tests: pin ink engine in _make_tui_argv npm-bootstrap tests (post-merge semantic fix)

Main's rewritten test_tui_npm_install.py tests call _make_tui_argv expecting
the Ink/npm flow unconditionally; with the dual-engine dispatch merged in,
_resolve_tui_engine() auto-selects opentui whenever ui-opentui/dist is built
in the repo, routing the call away from the path under test (first subprocess
became 'node --version' instead of 'npm run build'). Pin the engine to ink
via an autouse fixture, mirroring the existing pinning precedent in
test_tui_resume_flow.py.

tests/plugins/platforms/photon/test_auth.py

@@ -0,0 +1,609 @@
+"""Tests for the Photon auth module (device login + dashboard API)."""
+from __future__ import annotations
+
+import json
+import os
+from base64 import b64encode
+from pathlib import Path
+from typing import Any, Dict
+
+import pytest
+
+from plugins.platforms.photon import auth as photon_auth
+
+
+# ---------------------------------------------------------------------------
+# Fake httpx — we don't want to hit the real Photon API in unit tests.
+
+class _FakeResponse:
+    def __init__(
+        self,
+        *,
+        status: int = 200,
+        json_body: Any = None,
+        headers: Dict[str, str] | None = None,
+        text: str = "",
+    ) -> None:
+        self.status_code = status
+        self._json = json_body if json_body is not None else {}
+        self.headers = headers or {}
+        self.text = text
+
+    def json(self) -> Any:
+        return self._json
+
+    def raise_for_status(self) -> None:
+        if self.status_code >= 400:
+            raise RuntimeError(f"HTTP {self.status_code}")
+
+
+_PHOTON_ENV = (
+    "PHOTON_PROJECT_ID",
+    "PHOTON_PROJECT_SECRET",
+    "PHOTON_DASHBOARD_PROJECT_ID",
+    "PHOTON_SPECTRUM_HOST",
+    "PHOTON_ALLOWED_USERS",
+    "PHOTON_HOME_CHANNEL",
+)
+
+
+@pytest.fixture
+def tmp_hermes_home(tmp_path: Path, monkeypatch: pytest.MonkeyPatch):
+    home = tmp_path / "hermes"
+    home.mkdir()
+    monkeypatch.setenv("HERMES_HOME", str(home))
+    for key in _PHOTON_ENV:
+        monkeypatch.delenv(key, raising=False)
+    yield home
+    # save_env_value() mutates os.environ directly, so scrub any leakage.
+    for key in _PHOTON_ENV:
+        os.environ.pop(key, None)
+
+
+# ---------------------------------------------------------------------------
+# Credential storage
+
+def test_store_and_load_photon_token(tmp_hermes_home: Path) -> None:
+    photon_auth.store_photon_token("abc123def456")
+    assert photon_auth.load_photon_token() == "abc123def456"
+
+    auth_json = json.loads((tmp_hermes_home / "auth.json").read_text())
+    assert auth_json["credential_pool"]["photon"][0]["access_token"] == "abc123def456"
+
+
+def test_store_project_credentials_round_trip(
+    tmp_hermes_home: Path, monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    # Don't touch .env / os.environ here — exercise the auth.json path.
+    monkeypatch.setattr(photon_auth, "_persist_runtime_env", lambda *a, **k: None)
+    photon_auth.store_project_credentials(
+        spectrum_project_id="sp-123",
+        project_secret="secret-key",
+        dashboard_project_id="dash-456",
+        name="Hermes Agent",
+    )
+    for key in _PHOTON_ENV:
+        monkeypatch.delenv(key, raising=False)
+
+    sid, secret = photon_auth.load_project_credentials()
+    assert sid == "sp-123"
+    assert secret == "secret-key"
+    assert photon_auth.load_dashboard_project_id() == "dash-456"
+
+
+def test_store_project_credentials_writes_env(tmp_hermes_home: Path) -> None:
+    photon_auth.store_project_credentials(
+        spectrum_project_id="sp-789",
+        project_secret="sek-ret",
+        dashboard_project_id="dash-1",
+    )
+    env_text = (tmp_hermes_home / ".env").read_text()
+    assert "PHOTON_PROJECT_ID=sp-789" in env_text
+    assert "PHOTON_PROJECT_SECRET=sek-ret" in env_text
+
+
+def test_store_user_numbers_round_trip(tmp_hermes_home: Path) -> None:
+    photon_auth.store_user_numbers(
+        phone_number="+15551234567",
+        assigned_phone_number="+16282679185",
+        user_id="user-uuid",
+        dashboard_project_id="dash-uuid",
+    )
+
+    phone, assigned = photon_auth.load_user_numbers()
+    assert phone == "+15551234567"
+    assert assigned == "+16282679185"
+
+    summary = photon_auth.credential_summary()
+    assert summary["phone_number"] == "+15551234567"
+    assert summary["assigned_phone_number"] == "+16282679185"
+
+    rendered: list[str] = []
+    photon_auth.print_credential_summary(rendered.append)
+    assert "  my number           : +15551234567" in rendered[0]
+    assert "  assigned number     : +16282679185" in rendered[0]
+
+
+def test_load_user_numbers_falls_back_to_home_channel(
+    tmp_hermes_home: Path,
+) -> None:
+    from hermes_cli.config import save_env_value
+
+    save_env_value("PHOTON_HOME_CHANNEL", "+15551234567")
+
+    phone, assigned = photon_auth.load_user_numbers()
+    assert phone == "+15551234567"
+    assert assigned is None
+
+
+def test_refresh_user_numbers_reads_existing_assignment(
+    tmp_hermes_home: Path, monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    photon_auth.store_user_numbers(phone_number="+15551234567")
+
+    def fake_get(url: str, **kwargs: Any) -> _FakeResponse:
+        assert kwargs.get("headers", {}).get("Authorization") == (
+            "Basic " + b64encode(b"sp:secret").decode("ascii")
+        )
+        assert url.endswith("/projects/sp/users/")
+        return _FakeResponse(json_body={"succeed": True, "data": {"users": [{
+            "id": "user-uuid",
+            "phoneNumber": "+1 (555) 123-4567",
+            "assignedPhoneNumber": "+16282679185",
+        }]}})
+
+    monkeypatch.setattr(photon_auth.httpx, "get", fake_get)
+
+    phone, assigned = photon_auth.refresh_user_numbers("sp", "secret")
+    assert phone == "+15551234567"
+    assert assigned == "+16282679185"
+    assert photon_auth.load_user_numbers() == ("+15551234567", "+16282679185")
+
+
+def test_load_project_credentials_env_override(
+    tmp_hermes_home: Path, monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    monkeypatch.setattr(photon_auth, "_persist_runtime_env", lambda *a, **k: None)
+    photon_auth.store_project_credentials(
+        spectrum_project_id="from-file", project_secret="secret-file",
+    )
+    monkeypatch.setenv("PHOTON_PROJECT_ID", "from-env")
+    monkeypatch.setenv("PHOTON_PROJECT_SECRET", "secret-env")
+    sid, secret = photon_auth.load_project_credentials()
+    assert sid == "from-env"
+    assert secret == "secret-env"
+
+
+# ---------------------------------------------------------------------------
+# Device login flow
+
+def test_request_device_code_uses_photon_cli(monkeypatch: pytest.MonkeyPatch) -> None:
+    captured: Dict[str, Any] = {}
+
+    def fake_post(url: str, **kwargs: Any) -> _FakeResponse:
+        captured["url"] = url
+        captured["body"] = kwargs.get("json")
+        return _FakeResponse(json_body={
+            "device_code": "dev-code-xyz",
+            "user_code": "ABCD-1234",
+            "verification_uri": "https://app.photon.codes/device",
+            "verification_uri_complete": "https://app.photon.codes/device?code=ABCD-1234",
+            "expires_in": 600,
+            "interval": 5,
+        })
+
+    monkeypatch.setattr(photon_auth.httpx, "post", fake_post)
+
+    code = photon_auth.request_device_code()
+    assert code.device_code == "dev-code-xyz"
+    assert code.user_code == "ABCD-1234"
+    assert "/api/auth/device/code" in captured["url"]
+    # Hosted Photon allowlists registered device clients — an unregistered
+    # client_id is rejected with 400 invalid_client. We use Photon's published
+    # CLI device client and send the standard scope.
+    assert captured["body"]["client_id"] == "photon-cli"
+    assert captured["body"]["scope"] == "openid profile email"
+
+
+def _device_code() -> "photon_auth.DeviceCode":
+    return photon_auth.DeviceCode(
+        device_code="d", user_code="u",
+        verification_uri="https://x", verification_uri_complete=None,
+        expires_in=10, interval=0,
+    )
+
+
+def test_poll_for_token_body_access_token(monkeypatch: pytest.MonkeyPatch) -> None:
+    def fake_post(url: str, **kwargs: Any) -> _FakeResponse:
+        return _FakeResponse(status=200, json_body={"access_token": "tok-body"})
+
+    monkeypatch.setattr(photon_auth.httpx, "post", fake_post)
+    assert photon_auth.poll_for_token(_device_code(), interval=0, timeout=2) == "tok-body"
+
+
+def test_poll_for_token_session_fallback(monkeypatch: pytest.MonkeyPatch) -> None:
+    def fake_post(url: str, **kwargs: Any) -> _FakeResponse:
+        return _FakeResponse(status=200, json_body={"session": {"access_token": "tok-sess"}})
+
+    monkeypatch.setattr(photon_auth.httpx, "post", fake_post)
+    assert photon_auth.poll_for_token(_device_code(), interval=0, timeout=2) == "tok-sess"
+
+
+def test_poll_for_token_header_fallback(monkeypatch: pytest.MonkeyPatch) -> None:
+    def fake_post(url: str, **kwargs: Any) -> _FakeResponse:
+        return _FakeResponse(status=200, json_body={}, headers={"set-auth-token": "tok-hdr"})
+
+    monkeypatch.setattr(photon_auth.httpx, "post", fake_post)
+    assert photon_auth.poll_for_token(_device_code(), interval=0, timeout=2) == "tok-hdr"
+
+
+def test_poll_for_token_pending_then_success(monkeypatch: pytest.MonkeyPatch) -> None:
+    calls = {"n": 0}
+
+    def fake_post(url: str, **kwargs: Any) -> _FakeResponse:
+        calls["n"] += 1
+        if calls["n"] == 1:
+            return _FakeResponse(status=400, json_body={"error": "authorization_pending"})
+        return _FakeResponse(status=200, json_body={"access_token": "tok-eventual"})
+
+    monkeypatch.setattr(photon_auth.httpx, "post", fake_post)
+    assert photon_auth.poll_for_token(_device_code(), interval=0, timeout=5) == "tok-eventual"
+    assert calls["n"] == 2
+
+
+def test_poll_for_token_access_denied(monkeypatch: pytest.MonkeyPatch) -> None:
+    def fake_post(url: str, **kwargs: Any) -> _FakeResponse:
+        return _FakeResponse(status=400, json_body={"error": "access_denied"})
+
+    monkeypatch.setattr(photon_auth.httpx, "post", fake_post)
+    with pytest.raises(RuntimeError, match="access_denied"):
+        photon_auth.poll_for_token(_device_code(), interval=0, timeout=2)
+
+
+# ---------------------------------------------------------------------------
+# Projects
+
+def test_list_projects_unwraps_list(monkeypatch: pytest.MonkeyPatch) -> None:
+    def fake_get(url: str, **kwargs: Any) -> _FakeResponse:
+        return _FakeResponse(json_body=[{"id": "p1", "name": "Hermes Agent"}])
+
+    monkeypatch.setattr(photon_auth.httpx, "get", fake_get)
+    projects = photon_auth.list_projects("tok")
+    assert projects[0]["id"] == "p1"
+
+
+def test_find_project_by_name_case_insensitive(monkeypatch: pytest.MonkeyPatch) -> None:
+    def fake_get(url: str, **kwargs: Any) -> _FakeResponse:
+        return _FakeResponse(json_body={"data": [
+            {"id": "p1", "name": "Other"},
+            {"id": "p2", "name": "hermes agent"},
+        ]})
+
+    monkeypatch.setattr(photon_auth.httpx, "get", fake_get)
+    proj = photon_auth.find_project_by_name("tok", "Hermes Agent")
+    assert proj is not None and proj["id"] == "p2"
+
+
+def test_create_project_sends_spectrum_true(monkeypatch: pytest.MonkeyPatch) -> None:
+    captured: Dict[str, Any] = {}
+
+    def fake_post(url: str, **kwargs: Any) -> _FakeResponse:
+        captured["url"] = url
+        captured["body"] = kwargs.get("json")
+        captured["headers"] = kwargs.get("headers")
+        return _FakeResponse(json_body={"success": True, "id": "new-proj"})
+
+    monkeypatch.setattr(photon_auth.httpx, "post", fake_post)
+    data = photon_auth.create_project("tok", name="Hermes Agent")
+    assert data["id"] == "new-proj"
+    assert captured["body"]["spectrum"] is True
+    assert captured["body"]["name"] == "Hermes Agent"
+    assert captured["headers"]["Authorization"] == "Bearer tok"
+    assert captured["url"].endswith("/api/projects")
+
+
+def test_create_project_raises_without_id(monkeypatch: pytest.MonkeyPatch) -> None:
+    def fake_post(url: str, **kwargs: Any) -> _FakeResponse:
+        return _FakeResponse(json_body={"success": True})
+
+    monkeypatch.setattr(photon_auth.httpx, "post", fake_post)
+    with pytest.raises(RuntimeError, match="project id"):
+        photon_auth.create_project("tok")
+
+
+def test_ensure_spectrum_enabled_toggles_when_off(monkeypatch: pytest.MonkeyPatch) -> None:
+    get_calls = {"n": 0}
+    posted = {"toggle": False}
+
+    def fake_get(url: str, **kwargs: Any) -> _FakeResponse:
+        get_calls["n"] += 1
+        if get_calls["n"] == 1:
+            return _FakeResponse(json_body={"id": "p", "spectrum": False, "spectrumProjectId": None})
+        return _FakeResponse(json_body={"id": "p", "spectrum": True, "spectrumProjectId": "sp-1"})
+
+    def fake_post(url: str, **kwargs: Any) -> _FakeResponse:
+        if url.endswith("/spectrum/toggle"):
+            posted["toggle"] = True
+        return _FakeResponse(json_body={"success": True})
+
+    monkeypatch.setattr(photon_auth.httpx, "get", fake_get)
+    monkeypatch.setattr(photon_auth.httpx, "post", fake_post)
+    proj = photon_auth.ensure_spectrum_enabled("tok", "p")
+    assert posted["toggle"] is True
+    assert proj["spectrumProjectId"] == "sp-1"
+
+
+def test_ensure_spectrum_enabled_skips_toggle_when_on(monkeypatch: pytest.MonkeyPatch) -> None:
+    posted = {"toggle": False}
+
+    def fake_get(url: str, **kwargs: Any) -> _FakeResponse:
+        return _FakeResponse(json_body={"id": "p", "spectrum": True, "spectrumProjectId": "sp-1"})
+
+    def fake_post(url: str, **kwargs: Any) -> _FakeResponse:
+        if url.endswith("/spectrum/toggle"):
+            posted["toggle"] = True
+        return _FakeResponse(json_body={"success": True})
+
+    monkeypatch.setattr(photon_auth.httpx, "get", fake_get)
+    monkeypatch.setattr(photon_auth.httpx, "post", fake_post)
+    proj = photon_auth.ensure_spectrum_enabled("tok", "p")
+    assert posted["toggle"] is False
+    assert proj["spectrumProjectId"] == "sp-1"
+
+
+def test_regenerate_project_secret(monkeypatch: pytest.MonkeyPatch) -> None:
+    def fake_post(url: str, **kwargs: Any) -> _FakeResponse:
+        assert url.endswith("/regenerate-secret")
+        return _FakeResponse(json_body={"success": True, "projectSecret": "rotated"})
+
+    monkeypatch.setattr(photon_auth.httpx, "post", fake_post)
+    assert photon_auth.regenerate_project_secret("tok", "p") == "rotated"
+
+
+# ---------------------------------------------------------------------------
+# Users
+
+def test_create_user_rejects_invalid_phone() -> None:
+    with pytest.raises(ValueError, match="E.164"):
+        photon_auth.create_user("proj", "secret", phone_number="not-a-number")
+
+
+def test_create_user_posts_dashboard_shape(monkeypatch: pytest.MonkeyPatch) -> None:
+    captured: Dict[str, Any] = {}
+
+    def fake_post(url: str, **kwargs: Any) -> _FakeResponse:
+        captured["url"] = url
+        captured["body"] = kwargs.get("json")
+        captured["headers"] = kwargs.get("headers")
+        return _FakeResponse(json_body={"succeed": True, "data": {
+            "id": "user-uuid", "phoneNumber": "+15551234567",
+        }})
+
+    monkeypatch.setattr(photon_auth.httpx, "post", fake_post)
+    user = photon_auth.create_user("proj-id", "secret", phone_number="+15551234567")
+    assert user["id"] == "user-uuid"
+    assert captured["body"]["type"] == "shared"
+    assert captured["body"]["phoneNumber"] == "+15551234567"
+    assert captured["headers"]["Authorization"] == (
+        "Basic " + b64encode(b"proj-id:secret").decode("ascii")
+    )
+    assert captured["url"].endswith("/projects/proj-id/users/")
+
+
+def test_register_user_if_absent_dedup(monkeypatch: pytest.MonkeyPatch) -> None:
+    posted = {"n": 0}
+
+    def fake_get(url: str, **kwargs: Any) -> _FakeResponse:
+        return _FakeResponse(json_body={"succeed": True, "data": {"users": [{
+            "id": "u1",
+            "phoneNumber": "+1 (555) 123-4567",
+            "assignedPhoneNumber": "+16282679185",
+        }]}})
+
+    def fake_post(url: str, **kwargs: Any) -> _FakeResponse:
+        posted["n"] += 1
+        return _FakeResponse(json_body={"success": True, "user": {}})
+
+    monkeypatch.setattr(photon_auth.httpx, "get", fake_get)
+    monkeypatch.setattr(photon_auth.httpx, "post", fake_post)
+    # Same number, different formatting — should match and NOT create.
+    user, created = photon_auth.register_user_if_absent(
+        "proj", "secret", phone_number="+15551234567",
+    )
+    assert created is False
+    assert user["id"] == "u1"
+    assert posted["n"] == 0
+    # The reused user carries the assigned iMessage line ("TEXTS ON").
+    assert photon_auth.user_assigned_line(user) == "+16282679185"
+
+
+def test_user_assigned_line() -> None:
+    assert (
+        photon_auth.user_assigned_line({"assignedPhoneNumber": "+16282679185"})
+        == "+16282679185"
+    )
+    # Own number present but no assignment yet (e.g. freshly created user).
+    assert photon_auth.user_assigned_line({"phoneNumber": "+15551234567"}) is None
+    assert photon_auth.user_assigned_line({"assignedPhoneNumber": ""}) is None
+    assert photon_auth.user_assigned_line({}) is None
+    assert photon_auth.user_assigned_line(None) is None
+
+
+def test_register_user_if_absent_creates(monkeypatch: pytest.MonkeyPatch) -> None:
+    def fake_get(url: str, **kwargs: Any) -> _FakeResponse:
+        return _FakeResponse(json_body={"succeed": True, "data": {"users": []}})
+
+    def fake_post(url: str, **kwargs: Any) -> _FakeResponse:
+        return _FakeResponse(json_body={"succeed": True, "data": {"id": "u-new"}})
+
+    monkeypatch.setattr(photon_auth.httpx, "get", fake_get)
+    monkeypatch.setattr(photon_auth.httpx, "post", fake_post)
+    user, created = photon_auth.register_user_if_absent(
+        "proj", "secret", phone_number="+15551234567",
+    )
+    assert created is True
+    assert user["id"] == "u-new"
+
+
+# ---------------------------------------------------------------------------
+# Lines (assigned number)
+
+def test_get_imessage_line_returns_existing(monkeypatch: pytest.MonkeyPatch) -> None:
+    def fake_get(url: str, **kwargs: Any) -> _FakeResponse:
+        return _FakeResponse(json_body=[
+            {"id": "l1", "platform": "imessage", "phoneNumber": "+15559999999", "status": "active"},
+        ])
+
+    monkeypatch.setattr(photon_auth.httpx, "get", fake_get)
+    line = photon_auth.get_imessage_line("tok", "proj")
+    assert line is not None and line["phoneNumber"] == "+15559999999"
+
+
+def test_get_imessage_line_provisions_when_missing(monkeypatch: pytest.MonkeyPatch) -> None:
+    added = {"n": 0}
+
+    def fake_get(url: str, **kwargs: Any) -> _FakeResponse:
+        return _FakeResponse(json_body=[])
+
+    def fake_post(url: str, **kwargs: Any) -> _FakeResponse:
+        added["n"] += 1
+        assert kwargs.get("json", {}).get("platform") == "imessage"
+        return _FakeResponse(json_body={"success": True, "line": {
+            "id": "l-new", "platform": "imessage", "phoneNumber": "+15558888888",
+        }})
+
+    monkeypatch.setattr(photon_auth.httpx, "get", fake_get)
+    monkeypatch.setattr(photon_auth.httpx, "post", fake_post)
+    line = photon_auth.get_imessage_line("tok", "proj")
+    assert added["n"] == 1
+    assert line["phoneNumber"] == "+15558888888"
+
+
+# ---------------------------------------------------------------------------
+# Credential summary (no secret leakage)
+
+def test_credential_summary_no_secret_leak(
+    tmp_hermes_home: Path, monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    monkeypatch.setattr(photon_auth, "_persist_runtime_env", lambda *a, **k: None)
+    photon_auth.store_photon_token("token-aaaaaaaaaaaaaaaa")
+    photon_auth.store_project_credentials(
+        spectrum_project_id="sp-uuid",
+        project_secret="secret-bbbbbbbbbbb",
+        dashboard_project_id="dash-uuid",
+    )
+    summary = photon_auth.credential_summary()
+    blob = "\n".join(summary.values())
+    assert "token-aaaa" not in blob
+    assert "secret-bbbb" not in blob
+    assert summary["device_token"].startswith("✓")
+    assert summary["project_key"].startswith("✓")
+    assert summary["spectrum_project_id"] == "sp-uuid"
+    assert summary["dashboard_project_id"] == "dash-uuid"
+    assert summary["phone_number"].startswith("✗ missing")
+    assert summary["assigned_phone_number"].startswith("✗ missing")
+
+
+# ---------------------------------------------------------------------------
+# Device-token candidate extraction + dashboard validation.
+
+def test_device_response_candidates_covers_known_shapes() -> None:
+    candidates = photon_auth._device_response_token_candidates(
+        {
+            "access_token": "tok-snake",
+            "accessToken": "tok-camel",
+            "data": {"access_token": "tok-data"},
+        },
+        headers={"set-auth-token": "Bearer tok-header"},
+    )
+    by_source = {c.source: c.token for c in candidates}
+    assert by_source["access_token"] == "tok-snake"
+    assert by_source["accessToken"] == "tok-camel"
+    assert by_source["data.access_token"] == "tok-data"
+    # "Bearer " prefix is stripped from the header value.
+    assert by_source["set-auth-token"] == "tok-header"
+
+
+def test_device_response_candidates_dedupes() -> None:
+    candidates = photon_auth._device_response_token_candidates(
+        {"access_token": "same", "accessToken": "same"},
+    )
+    assert [c.token for c in candidates] == ["same"]
+
+
+def test_validate_photon_token_rejects_unrecognized_session(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    def fake_get(url: str, *, headers: Dict[str, str], timeout: float) -> _FakeResponse:
+        if url.endswith("/api/auth/get-session"):
+            return _FakeResponse(json_body={})  # no "user" key
+        return _FakeResponse(json_body=[])
+
+    monkeypatch.setattr(photon_auth.httpx, "get", fake_get)
+    with pytest.raises(photon_auth.PhotonDashboardAuthError):
+        photon_auth.validate_photon_token("some-token")
+
+
+def test_validate_photon_token_rejects_project_api_denial(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    def fake_get(url: str, *, headers: Dict[str, str], timeout: float) -> _FakeResponse:
+        if url.endswith("/api/auth/get-session"):
+            return _FakeResponse(json_body={"user": {"id": "u1"}})
+        return _FakeResponse(status=403)  # project API rejects
+
+    monkeypatch.setattr(photon_auth.httpx, "get", fake_get)
+    with pytest.raises(photon_auth.PhotonDashboardAuthError):
+        photon_auth.validate_photon_token("some-token")
+
+
+def test_login_device_flow_validates_before_persisting(
+    tmp_hermes_home: Path, monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    def fake_post(url: str, *, json: Dict[str, Any], timeout: float) -> _FakeResponse:
+        if url.endswith("/api/auth/device/code"):
+            return _FakeResponse(json_body={
+                "device_code": "dev", "user_code": "AAAA",
+                "verification_uri": "https://app.photon.codes/device",
+                "verification_uri_complete": None,
+                "expires_in": 600, "interval": 0,
+            })
+        # device/token approval
+        return _FakeResponse(json_body={"access_token": "good-token"})
+
+    def fake_get(url: str, *, headers: Dict[str, str], timeout: float) -> _FakeResponse:
+        if url.endswith("/api/auth/get-session"):
+            return _FakeResponse(json_body={"user": {"id": "u1"}})
+        return _FakeResponse(json_body=[])  # projects OK
+
+    monkeypatch.setattr(photon_auth.httpx, "post", fake_post)
+    monkeypatch.setattr(photon_auth.httpx, "get", fake_get)
+
+    token = photon_auth.login_device_flow(open_browser=False)
+    assert token == "good-token"
+    assert photon_auth.load_photon_token() == "good-token"
+
+
+def test_login_device_flow_raises_when_token_invalid(
+    tmp_hermes_home: Path, monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    def fake_post(url: str, *, json: Dict[str, Any], timeout: float) -> _FakeResponse:
+        if url.endswith("/api/auth/device/code"):
+            return _FakeResponse(json_body={
+                "device_code": "dev", "user_code": "AAAA",
+                "verification_uri": "https://app.photon.codes/device",
+                "verification_uri_complete": None,
+                "expires_in": 600, "interval": 0,
+            })
+        return _FakeResponse(json_body={"access_token": "bad-token"})
+
+    def fake_get(url: str, *, headers: Dict[str, str], timeout: float) -> _FakeResponse:
+        return _FakeResponse(status=401)  # session lookup rejects
+
+    monkeypatch.setattr(photon_auth.httpx, "post", fake_post)
+    monkeypatch.setattr(photon_auth.httpx, "get", fake_get)
+
+    with pytest.raises(photon_auth.PhotonDashboardAuthError):
+        photon_auth.login_device_flow(open_browser=False)
+    # A token that failed validation must never be persisted.
+    assert photon_auth.load_photon_token() is None

tests/plugins/platforms/photon/test_inbound.py

@@ -0,0 +1,314 @@
+"""Inbound dispatch + dedup tests for PhotonAdapter.
+
+These bypass the loopback HTTP stream — they call ``_dispatch_inbound`` /
+``_on_inbound_line`` / ``_is_duplicate`` directly, exercising the
+sidecar-event parsing without spawning the Node sidecar or binding ports.
+"""
+from __future__ import annotations
+
+import base64
+import json
+from pathlib import Path
+from typing import Any, Dict, List
+
+import pytest
+
+from gateway.config import Platform, PlatformConfig
+from gateway.platforms.base import MessageEvent, MessageType
+from plugins.platforms.photon.adapter import PhotonAdapter
+
+
+def _make_adapter(monkeypatch: pytest.MonkeyPatch) -> PhotonAdapter:
+    monkeypatch.setenv("PHOTON_PROJECT_ID", "test-project-id")
+    monkeypatch.setenv("PHOTON_PROJECT_SECRET", "test-project-secret")
+    cfg = PlatformConfig(enabled=True, token="", extra={})
+    return PhotonAdapter(cfg)
+
+
+def _capture(adapter: PhotonAdapter, monkeypatch: pytest.MonkeyPatch) -> List[MessageEvent]:
+    captured: List[MessageEvent] = []
+
+    async def fake_handle(event: MessageEvent) -> None:
+        captured.append(event)
+
+    monkeypatch.setattr(adapter, "handle_message", fake_handle)
+    return captured
+
+
+def _dm_event(text: str, msg_id: str = "spc-msg-abc") -> Dict[str, Any]:
+    return {
+        "messageId": msg_id,
+        "platform": "iMessage",
+        "space": {"id": "+15551234567", "type": "dm", "phone": "+15551234567"},
+        "sender": {"id": "+15551234567"},
+        "content": {"type": "text", "text": text},
+        "timestamp": "2026-05-14T19:06:32.000Z",
+    }
+
+
+@pytest.mark.asyncio
+async def test_dispatch_text_dm(monkeypatch: pytest.MonkeyPatch) -> None:
+    adapter = _make_adapter(monkeypatch)
+    captured = _capture(adapter, monkeypatch)
+
+    await adapter._dispatch_inbound(_dm_event("hello world"))
+
+    assert len(captured) == 1
+    event = captured[0]
+    assert event.text == "hello world"
+    assert event.message_type == MessageType.TEXT
+    assert event.message_id == "spc-msg-abc"
+    src = event.source
+    assert src is not None
+    assert src.platform == Platform("photon")
+    assert src.chat_id == "+15551234567"
+    assert src.chat_type == "dm"
+    assert src.user_id == "+15551234567"
+
+
+@pytest.mark.asyncio
+async def test_dispatch_group_type(monkeypatch: pytest.MonkeyPatch) -> None:
+    adapter = _make_adapter(monkeypatch)
+    captured = _capture(adapter, monkeypatch)
+
+    event = {
+        "messageId": "spc-msg-grp",
+        "space": {"id": "group-guid-xyz", "type": "group", "phone": None},
+        "sender": {"id": "+15551234567"},
+        "content": {"type": "text", "text": "hi group"},
+        "timestamp": "2026-05-14T19:06:32.000Z",
+    }
+    await adapter._dispatch_inbound(event)
+    assert captured[0].source.chat_type == "group"
+
+
+# A real 1x1 transparent PNG (passes base.py's _looks_like_image magic check).
+_PNG_1X1_B64 = (
+    "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNkYPhf"
+    "DwAChwGA60e6kgAAAABJRU5ErkJggg=="
+)
+
+
+def _attachment_event(
+    content: Dict[str, Any], msg_id: str = "spc-msg-att"
+) -> Dict[str, Any]:
+    return {
+        "messageId": msg_id,
+        "space": {"id": "+15551234567", "type": "dm", "phone": "+15551234567"},
+        "sender": {"id": "+15551234567"},
+        "content": {"type": "attachment", **content},
+        "timestamp": "2026-05-14T19:06:32.000Z",
+    }
+
+
+def _voice_event(
+    content: Dict[str, Any], msg_id: str = "spc-msg-voice"
+) -> Dict[str, Any]:
+    return {
+        "messageId": msg_id,
+        "space": {"id": "+15551234567", "type": "dm", "phone": "+15551234567"},
+        "sender": {"id": "+15551234567"},
+        "content": {"type": "voice", **content},
+        "timestamp": "2026-05-14T19:06:32.000Z",
+    }
+
+
+@pytest.mark.asyncio
+async def test_dispatch_attachment_without_bytes_surfaces_marker(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    """No inline ``data`` (over cap / failed sidecar read) -> text marker, no media."""
+    adapter = _make_adapter(monkeypatch)
+    captured = _capture(adapter, monkeypatch)
+
+    event = _attachment_event(
+        {"name": "IMG_4127.HEIC", "mimeType": "image/heic", "size": 12345}
+    )
+    await adapter._dispatch_inbound(event)
+    assert len(captured) == 1
+    ev = captured[0]
+    assert "Photon attachment received" in ev.text
+    assert "IMG_4127.HEIC" in ev.text
+    assert ev.message_type == MessageType.PHOTO
+    assert ev.media_urls == []
+    assert ev.media_types == []
+
+
+@pytest.mark.asyncio
+async def test_dispatch_attachment_downloads_image(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    """Inline base64 image bytes are decoded, cached, and exposed as media."""
+    adapter = _make_adapter(monkeypatch)
+    captured = _capture(adapter, monkeypatch)
+
+    raw = base64.b64decode(_PNG_1X1_B64)
+    event = _attachment_event(
+        {
+            "name": "photo.png",
+            "mimeType": "image/png",
+            "size": len(raw),
+            "data": _PNG_1X1_B64,
+            "encoding": "base64",
+        }
+    )
+    await adapter._dispatch_inbound(event)
+
+    assert len(captured) == 1
+    ev = captured[0]
+    assert ev.message_type == MessageType.PHOTO
+    assert ev.media_types == ["image/png"]
+    assert len(ev.media_urls) == 1
+    cached = Path(ev.media_urls[0])
+    try:
+        assert cached.is_file()
+        assert cached.read_bytes() == raw
+        assert ev.text == "(attachment)"
+    finally:
+        cached.unlink(missing_ok=True)
+
+
+@pytest.mark.asyncio
+async def test_dispatch_voice_downloads_audio(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    """Inbound Spectrum voice content is cached and routed to auto-STT."""
+    adapter = _make_adapter(monkeypatch)
+    captured = _capture(adapter, monkeypatch)
+
+    raw = b"OggS" + b"\x00" * 32
+    event = _voice_event(
+        {
+            "name": "note.ogg",
+            "mimeType": "audio/ogg",
+            "duration": 7,
+            "size": len(raw),
+            "data": base64.b64encode(raw).decode("ascii"),
+            "encoding": "base64",
+        }
+    )
+    await adapter._dispatch_inbound(event)
+
+    assert len(captured) == 1
+    ev = captured[0]
+    assert ev.message_type == MessageType.VOICE
+    assert ev.media_types == ["audio/ogg"]
+    assert len(ev.media_urls) == 1
+    cached = Path(ev.media_urls[0])
+    try:
+        assert cached.is_file()
+        assert cached.read_bytes() == raw
+        assert ev.text == "(voice)"
+    finally:
+        cached.unlink(missing_ok=True)
+
+
+@pytest.mark.asyncio
+async def test_dispatch_voice_without_bytes_surfaces_marker(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    """Metadata-only voice still tells the agent a voice note arrived."""
+    adapter = _make_adapter(monkeypatch)
+    captured = _capture(adapter, monkeypatch)
+
+    event = _voice_event(
+        {"name": "note.m4a", "mimeType": "audio/mp4", "duration": 12, "size": 12345}
+    )
+    await adapter._dispatch_inbound(event)
+
+    assert len(captured) == 1
+    ev = captured[0]
+    assert "Photon voice received" in ev.text
+    assert "note.m4a" in ev.text
+    assert "duration: 12s" in ev.text
+    assert ev.message_type == MessageType.VOICE
+    assert ev.media_urls == []
+    assert ev.media_types == []
+
+
+@pytest.mark.asyncio
+async def test_dispatch_attachment_downloads_document(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    """Non-image attachments route through the document cache as DOCUMENT."""
+    adapter = _make_adapter(monkeypatch)
+    captured = _capture(adapter, monkeypatch)
+
+    raw = b"%PDF-1.4 hermes test document"
+    event = _attachment_event(
+        {
+            "name": "report.pdf",
+            "mimeType": "application/pdf",
+            "size": len(raw),
+            "data": base64.b64encode(raw).decode("ascii"),
+            "encoding": "base64",
+        }
+    )
+    await adapter._dispatch_inbound(event)
+
+    assert len(captured) == 1
+    ev = captured[0]
+    assert ev.message_type == MessageType.DOCUMENT
+    assert ev.media_types == ["application/pdf"]
+    assert len(ev.media_urls) == 1
+    cached = Path(ev.media_urls[0])
+    try:
+        assert cached.is_file()
+        assert cached.read_bytes() == raw
+        assert ev.text == "(attachment)"
+    finally:
+        cached.unlink(missing_ok=True)
+
+
+@pytest.mark.asyncio
+async def test_on_inbound_line_dispatches_and_dedups(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    adapter = _make_adapter(monkeypatch)
+    captured = _capture(adapter, monkeypatch)
+
+    line = json.dumps(_dm_event("ping", msg_id="dup-1"))
+    await adapter._on_inbound_line(line)
+    await adapter._on_inbound_line(line)  # same messageId -> deduped
+
+    assert len(captured) == 1
+    assert captured[0].text == "ping"
+
+
+@pytest.mark.asyncio
+async def test_on_inbound_line_ignores_bad_json(monkeypatch: pytest.MonkeyPatch) -> None:
+    adapter = _make_adapter(monkeypatch)
+    captured = _capture(adapter, monkeypatch)
+
+    await adapter._on_inbound_line("{not json")
+    assert captured == []
+
+
+def test_is_duplicate_window(monkeypatch: pytest.MonkeyPatch) -> None:
+    adapter = _make_adapter(monkeypatch)
+    assert adapter._is_duplicate("id-1") is False
+    assert adapter._is_duplicate("id-1") is True
+    assert adapter._is_duplicate("id-2") is False
+    assert adapter._is_duplicate("id-1") is True  # still dup
+
+
+def test_is_duplicate_hard_size_bound(monkeypatch: pytest.MonkeyPatch) -> None:
+    # A burst of unique ids within the window must not grow the dedup map past
+    # its bound — evict oldest (LRU), not only expired entries.
+    import plugins.platforms.photon.adapter as ad
+
+    monkeypatch.setattr(ad, "_DEDUP_MAX_SIZE", 5)
+    adapter = _make_adapter(monkeypatch)
+    for i in range(100):
+        adapter._is_duplicate(f"id-{i}")
+    assert len(adapter._seen_messages) <= 5
+    assert adapter._is_duplicate("id-99") is True  # recent still deduped
+    assert adapter._is_duplicate("id-0") is False  # oldest evicted
+
+
+def test_check_requirements_without_node(monkeypatch: pytest.MonkeyPatch) -> None:
+    # If no node binary on PATH the adapter should refuse to start.
+    from plugins.platforms.photon import adapter as adapter_mod
+
+    monkeypatch.setattr(adapter_mod.shutil, "which", lambda _name: None)
+    assert adapter_mod.check_requirements() is False

tests/plugins/platforms/photon/test_mention_gating.py

@@ -0,0 +1,138 @@
+"""Group-chat mention-gating tests for PhotonAdapter.
+
+Parity with the BlueBubbles iMessage channel: when ``require_mention`` is
+enabled, group messages are dropped unless they hit a wake-word pattern,
+and the leading wake word is stripped from the ones that pass. DMs are
+never gated.
+
+These call ``_dispatch_inbound`` directly (no aiohttp / ports) and assert
+on what reaches ``handle_message``.
+"""
+from __future__ import annotations
+
+from typing import List
+
+import pytest
+
+from gateway.config import PlatformConfig
+from gateway.platforms.base import MessageEvent
+from plugins.platforms.photon.adapter import PhotonAdapter
+
+
+def _make_adapter(monkeypatch: pytest.MonkeyPatch, extra: dict | None = None) -> PhotonAdapter:
+    monkeypatch.setenv("PHOTON_PROJECT_ID", "test-project-id")
+    monkeypatch.setenv("PHOTON_PROJECT_SECRET", "test-project-secret")
+    monkeypatch.delenv("PHOTON_REQUIRE_MENTION", raising=False)
+    monkeypatch.delenv("PHOTON_MENTION_PATTERNS", raising=False)
+    cfg = PlatformConfig(enabled=True, token="", extra=extra or {})
+    return PhotonAdapter(cfg)
+
+
+def _group_payload(text: str) -> dict:
+    return {
+        "messageId": f"grp-{abs(hash(text))}",
+        "space": {"id": "group-guid-xyz", "type": "group", "phone": None},
+        "sender": {"id": "+15551234567"},
+        "content": {"type": "text", "text": text},
+        "timestamp": "2026-05-14T19:06:32.000Z",
+    }
+
+
+def _dm_payload(text: str) -> dict:
+    return {
+        "messageId": f"dm-{abs(hash(text))}",
+        "space": {"id": "+15551234567", "type": "dm", "phone": "+15551234567"},
+        "sender": {"id": "+15551234567"},
+        "content": {"type": "text", "text": text},
+        "timestamp": "2026-05-14T19:06:32.000Z",
+    }
+
+
+def _capture(adapter: PhotonAdapter, monkeypatch: pytest.MonkeyPatch) -> List[MessageEvent]:
+    captured: List[MessageEvent] = []
+
+    async def fake_handle(event: MessageEvent) -> None:
+        captured.append(event)
+
+    monkeypatch.setattr(adapter, "handle_message", fake_handle)
+    return captured
+
+
+def test_require_mention_defaults_off(monkeypatch: pytest.MonkeyPatch) -> None:
+    adapter = _make_adapter(monkeypatch)
+    assert adapter.require_mention is False
+    # Defaults compile to the two Hermes wake-word patterns.
+    assert len(adapter._mention_patterns) == 2
+
+
+@pytest.mark.asyncio
+async def test_group_message_dropped_without_mention(monkeypatch: pytest.MonkeyPatch) -> None:
+    adapter = _make_adapter(monkeypatch, extra={"require_mention": True})
+    captured = _capture(adapter, monkeypatch)
+
+    await adapter._dispatch_inbound(_group_payload("just chatting, no wake word"))
+    assert captured == []
+
+
+@pytest.mark.asyncio
+async def test_group_message_passes_and_strips_wake_word(monkeypatch: pytest.MonkeyPatch) -> None:
+    adapter = _make_adapter(monkeypatch, extra={"require_mention": True})
+    captured = _capture(adapter, monkeypatch)
+
+    await adapter._dispatch_inbound(_group_payload("Hermes what's the weather"))
+    assert len(captured) == 1
+    # Leading wake word stripped before dispatch.
+    assert captured[0].text == "what's the weather"
+
+
+@pytest.mark.asyncio
+async def test_dm_never_gated(monkeypatch: pytest.MonkeyPatch) -> None:
+    adapter = _make_adapter(monkeypatch, extra={"require_mention": True})
+    captured = _capture(adapter, monkeypatch)
+
+    await adapter._dispatch_inbound(_dm_payload("no wake word here"))
+    assert len(captured) == 1
+    assert captured[0].text == "no wake word here"
+
+
+@pytest.mark.asyncio
+async def test_require_mention_off_passes_group_messages(monkeypatch: pytest.MonkeyPatch) -> None:
+    adapter = _make_adapter(monkeypatch)  # require_mention defaults off
+    captured = _capture(adapter, monkeypatch)
+
+    await adapter._dispatch_inbound(_group_payload("plain group chatter"))
+    assert len(captured) == 1
+    assert captured[0].text == "plain group chatter"
+
+
+def test_custom_mention_patterns_from_config(monkeypatch: pytest.MonkeyPatch) -> None:
+    adapter = _make_adapter(
+        monkeypatch,
+        extra={"require_mention": True, "mention_patterns": [r"(?<![\w@])@?amos\b[,:\-]?"]},
+    )
+    assert adapter.require_mention is True
+    assert len(adapter._mention_patterns) == 1
+    assert adapter._message_matches_mention_patterns("amos help me") is True
+    assert adapter._message_matches_mention_patterns("hermes help me") is False
+
+
+def test_mention_patterns_env_comma_separated(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setenv("PHOTON_PROJECT_ID", "test-project-id")
+    monkeypatch.setenv("PHOTON_PROJECT_SECRET", "test-project-secret")
+    monkeypatch.setenv("PHOTON_REQUIRE_MENTION", "true")
+    monkeypatch.setenv("PHOTON_MENTION_PATTERNS", r"bot\b, assistant\b")
+    cfg = PlatformConfig(enabled=True, token="", extra={})
+    adapter = PhotonAdapter(cfg)
+    assert adapter.require_mention is True
+    assert len(adapter._mention_patterns) == 2
+    assert adapter._message_matches_mention_patterns("hey bot") is True
+
+
+def test_invalid_pattern_skipped(monkeypatch: pytest.MonkeyPatch) -> None:
+    adapter = _make_adapter(
+        monkeypatch,
+        extra={"require_mention": True, "mention_patterns": ["(unclosed", r"good\b"]},
+    )
+    # Bad regex dropped, good one kept.
+    assert len(adapter._mention_patterns) == 1
+    assert adapter._message_matches_mention_patterns("a good thing") is True

tests/plugins/platforms/photon/test_outbound_media.py

@@ -0,0 +1,255 @@
+"""Outbound-media tests for PhotonAdapter.
+
+Photon ships outbound attachments via spectrum-ts' ``attachment()`` /
+``voice()`` content builders, reached through the Node sidecar's
+``/send-attachment`` endpoint. These tests stub ``_sidecar_call`` so we
+can assert the endpoint + body shape each ``send_*`` override produces
+without spawning Node or binding ports.
+"""
+from __future__ import annotations
+
+import os
+from typing import Any, Dict, List, Tuple
+
+import pytest
+
+from gateway.config import PlatformConfig
+from plugins.platforms.photon import adapter as photon_adapter
+from plugins.platforms.photon.adapter import PhotonAdapter
+
+
+def _make_adapter(monkeypatch: pytest.MonkeyPatch) -> PhotonAdapter:
+    monkeypatch.setenv("PHOTON_PROJECT_ID", "test-project-id")
+    monkeypatch.setenv("PHOTON_PROJECT_SECRET", "test-project-secret")
+    monkeypatch.delenv("PHOTON_WEBHOOK_SECRET", raising=False)
+    cfg = PlatformConfig(enabled=True, token="", extra={})
+    return PhotonAdapter(cfg)
+
+
+def _capture_sidecar(adapter: PhotonAdapter) -> List[Tuple[str, Dict[str, Any]]]:
+    """Replace ``_sidecar_call`` with a recorder that returns a fixed id."""
+    calls: List[Tuple[str, Dict[str, Any]]] = []
+
+    async def _fake_call(path: str, body: Dict[str, Any]) -> Dict[str, Any]:
+        calls.append((path, body))
+        return {"ok": True, "messageId": "msg-123"}
+
+    adapter._sidecar_call = _fake_call  # type: ignore[assignment]
+    return calls
+
+
+@pytest.fixture()
+def real_file(tmp_path) -> str:
+    p = tmp_path / "photo.jpg"
+    p.write_bytes(b"\xff\xd8\xff\xe0fake-jpeg")
+    return str(p)
+
+
+def _patch_safe_path(monkeypatch: pytest.MonkeyPatch) -> None:
+    """Make path validation a passthrough so tmp files outside the cache pass."""
+    monkeypatch.setattr(
+        PhotonAdapter,
+        "validate_media_delivery_path",
+        staticmethod(lambda p: p if os.path.exists(p) else None),
+    )
+
+
+@pytest.mark.asyncio
+async def test_send_image_file_hits_attachment_endpoint(
+    monkeypatch: pytest.MonkeyPatch, real_file: str
+) -> None:
+    _patch_safe_path(monkeypatch)
+    adapter = _make_adapter(monkeypatch)
+    calls = _capture_sidecar(adapter)
+
+    result = await adapter.send_image_file(
+        "any;-;+15551234567", real_file, caption="look"
+    )
+
+    assert result.success is True
+    assert result.message_id == "msg-123"
+    assert len(calls) == 1
+    path, body = calls[0]
+    assert path == "/send-attachment"
+    assert body["spaceId"] == "any;-;+15551234567"
+    assert body["path"] == real_file
+    assert body["kind"] == "attachment"
+    assert body["caption"] == "look"
+    assert body["mimeType"] == "image/jpeg"  # inferred from .jpg
+
+
+@pytest.mark.asyncio
+async def test_send_voice_marks_kind_voice(
+    monkeypatch: pytest.MonkeyPatch, tmp_path
+) -> None:
+    _patch_safe_path(monkeypatch)
+    audio = tmp_path / "note.m4a"
+    audio.write_bytes(b"fake-audio")
+    adapter = _make_adapter(monkeypatch)
+    calls = _capture_sidecar(adapter)
+
+    result = await adapter.send_voice("any;-;+1", str(audio))
+
+    assert result.success is True
+    path, body = calls[0]
+    assert path == "/send-attachment"
+    assert body["kind"] == "voice"
+
+
+@pytest.mark.asyncio
+async def test_send_document_passes_filename(
+    monkeypatch: pytest.MonkeyPatch, tmp_path
+) -> None:
+    _patch_safe_path(monkeypatch)
+    doc = tmp_path / "report.pdf"
+    doc.write_bytes(b"%PDF-1.4 fake")
+    adapter = _make_adapter(monkeypatch)
+    calls = _capture_sidecar(adapter)
+
+    await adapter.send_document("any;-;+1", str(doc), file_name="Q3.pdf")
+
+    _, body = calls[0]
+    assert body["kind"] == "attachment"
+    assert body["name"] == "Q3.pdf"
+    assert body["mimeType"] == "application/pdf"
+
+
+@pytest.mark.asyncio
+async def test_send_video_passes_through(
+    monkeypatch: pytest.MonkeyPatch, tmp_path
+) -> None:
+    _patch_safe_path(monkeypatch)
+    vid = tmp_path / "clip.mp4"
+    vid.write_bytes(b"fake-mp4")
+    adapter = _make_adapter(monkeypatch)
+    calls = _capture_sidecar(adapter)
+
+    await adapter.send_video("any;+;groupguid", str(vid), caption="watch")
+
+    _, body = calls[0]
+    assert body["kind"] == "attachment"
+    assert body["caption"] == "watch"
+
+
+@pytest.mark.asyncio
+async def test_send_image_url_caches_then_sends_attachment(
+    monkeypatch: pytest.MonkeyPatch, real_file: str
+) -> None:
+    _patch_safe_path(monkeypatch)
+    adapter = _make_adapter(monkeypatch)
+    calls = _capture_sidecar(adapter)
+
+    async def _fake_cache(url: str, *a, **k) -> str:
+        assert url == "https://example.com/cat.jpg"
+        return real_file
+
+    import gateway.platforms.base as base_mod
+
+    monkeypatch.setattr(base_mod, "cache_image_from_url", _fake_cache)
+
+    result = await adapter.send_image(
+        "any;-;+1", "https://example.com/cat.jpg", caption="cat"
+    )
+
+    assert result.success is True
+    path, body = calls[0]
+    assert path == "/send-attachment"
+    assert body["path"] == real_file
+    assert body["caption"] == "cat"
+
+
+@pytest.mark.asyncio
+async def test_send_image_url_fetch_failure_falls_back_to_text(
+    monkeypatch: pytest.MonkeyPatch
+) -> None:
+    adapter = _make_adapter(monkeypatch)
+    calls = _capture_sidecar(adapter)
+
+    async def _boom(url: str, *a, **k) -> str:
+        raise RuntimeError("network down")
+
+    import gateway.platforms.base as base_mod
+
+    monkeypatch.setattr(base_mod, "cache_image_from_url", _boom)
+
+    result = await adapter.send_image(
+        "any;-;+1", "https://example.com/cat.jpg", caption="cat"
+    )
+
+    # Fallback path: base send_image() routes to send() → /send (text).
+    assert result.success is True
+    assert calls[0][0] == "/send"
+    assert "https://example.com/cat.jpg" in calls[0][1]["text"]
+
+
+@pytest.mark.asyncio
+async def test_send_attachment_rejects_unsafe_path(
+    monkeypatch: pytest.MonkeyPatch
+) -> None:
+    # Default validation (no passthrough patch) should reject a nonexistent /
+    # traversal path, returning a failed SendResult without calling the sidecar.
+    monkeypatch.setattr(
+        PhotonAdapter,
+        "validate_media_delivery_path",
+        staticmethod(lambda p: None),
+    )
+    adapter = _make_adapter(monkeypatch)
+    calls = _capture_sidecar(adapter)
+
+    result = await adapter.send_image_file("any;-;+1", "/etc/passwd")
+
+    assert result.success is False
+    assert "unsafe" in (result.error or "")
+    assert calls == []  # never reached the sidecar
+
+
+@pytest.mark.asyncio
+async def test_standalone_send_text_then_attachments(
+    monkeypatch: pytest.MonkeyPatch, tmp_path
+) -> None:
+    _patch_safe_path(monkeypatch)
+    img = tmp_path / "a.png"
+    img.write_bytes(b"\x89PNG fake")
+    monkeypatch.setenv("PHOTON_SIDECAR_TOKEN", "tok")
+
+    posted: List[Tuple[str, Dict[str, Any]]] = []
+
+    class _Resp:
+        status_code = 200
+
+        @staticmethod
+        def json() -> Dict[str, Any]:
+            return {"ok": True, "messageId": "m-9"}
+
+    class _FakeClient:
+        def __init__(self, *a, **k):
+            pass
+
+        async def __aenter__(self):
+            return self
+
+        async def __aexit__(self, *a):
+            return False
+
+        async def post(self, url: str, json: Dict[str, Any], headers=None):
+            posted.append((url, json))
+            return _Resp()
+
+    monkeypatch.setattr(photon_adapter.httpx, "AsyncClient", _FakeClient)
+
+    cfg = PlatformConfig(enabled=True, token="", extra={})
+    result = await photon_adapter._standalone_send(
+        cfg,
+        "any;-;+1",
+        "hello",
+        media_files=[(str(img), False)],
+    )
+
+    assert result.get("success") is True
+    # First call is the text /send, second is /send-attachment.
+    assert posted[0][0].endswith("/send")
+    assert posted[0][1]["text"] == "hello"
+    assert posted[1][0].endswith("/send-attachment")
+    assert posted[1][1]["path"] == str(img)
+    assert posted[1][1]["kind"] == "attachment"
+    assert posted[1][1]["mimeType"] == "image/png"

tests/plugins/platforms/photon/test_setup_access.py

@@ -0,0 +1,69 @@
+"""Tests for `hermes photon setup`'s access auto-configuration.
+
+`_autoconfigure_access` allowlists the operator and points the cron home
+channel at their DM, writing to the per-test ~/.hermes/.env (the hermetic
+HERMES_HOME fixture isolates this). It must fill only unset keys so a re-run
+never clobbers a hand-tuned allowlist.
+"""
+from __future__ import annotations
+
+import pytest
+
+from hermes_cli.config import get_env_value, save_env_value
+from plugins.platforms.photon.adapter import _env_enablement
+from plugins.platforms.photon import cli
+
+
+def test_autoconfigure_access_fills_unset(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.delenv("PHOTON_ALLOWED_USERS", raising=False)
+    monkeypatch.delenv("PHOTON_HOME_CHANNEL", raising=False)
+
+    cli._autoconfigure_access("+15551234567")
+
+    assert get_env_value("PHOTON_ALLOWED_USERS") == "+15551234567"
+    assert get_env_value("PHOTON_HOME_CHANNEL") == "+15551234567"
+
+
+def test_autoconfigure_access_preserves_existing_allowlist(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    monkeypatch.delenv("PHOTON_ALLOWED_USERS", raising=False)
+    monkeypatch.delenv("PHOTON_HOME_CHANNEL", raising=False)
+    # A hand-tuned allowlist already in place must survive a setup re-run.
+    save_env_value("PHOTON_ALLOWED_USERS", "+19998887777,+15551112222")
+
+    cli._autoconfigure_access("+15551234567")
+
+    assert get_env_value("PHOTON_ALLOWED_USERS") == "+19998887777,+15551112222"
+    # The still-unset home channel is filled.
+    assert get_env_value("PHOTON_HOME_CHANNEL") == "+15551234567"
+
+
+def test_env_enablement_seeds_home_channel(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setenv("PHOTON_PROJECT_ID", "project_123")
+    monkeypatch.setenv("PHOTON_PROJECT_SECRET", "secret_123")
+    monkeypatch.setenv("PHOTON_HOME_CHANNEL", "+15551234567")
+    monkeypatch.setenv("PHOTON_HOME_CHANNEL_NAME", "Primary DM")
+
+    seed = _env_enablement()
+
+    assert seed is not None
+    assert seed["home_channel"] == {
+        "chat_id": "+15551234567",
+        "name": "Primary DM",
+    }
+
+
+def test_env_enablement_home_channel_defaults_name(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setenv("PHOTON_PROJECT_ID", "project_123")
+    monkeypatch.setenv("PHOTON_PROJECT_SECRET", "secret_123")
+    monkeypatch.setenv("PHOTON_HOME_CHANNEL", "+15551234567")
+    monkeypatch.delenv("PHOTON_HOME_CHANNEL_NAME", raising=False)
+
+    seed = _env_enablement()
+
+    assert seed is not None
+    assert seed["home_channel"] == {
+        "chat_id": "+15551234567",
+        "name": "Home",
+    }

tests/plugins/test_discord_runtime_failure.py

@@ -0,0 +1,59 @@
+import asyncio
+from unittest.mock import AsyncMock
+
+import pytest
+
+from gateway.config import PlatformConfig
+from plugins.platforms.discord.adapter import DiscordAdapter
+
+
+@pytest.mark.asyncio
+async def test_discord_bot_task_runtime_exit_notifies_gateway_for_reconnect(monkeypatch):
+    """A post-ready discord.py websocket task crash must not leave the gateway split-brained.
+
+    Regression: producers stayed systemd-active while Discord stopped responding after
+    a runtime ClientOSError/ConnectionResetError. The adapter must mark Discord as a
+    retryable fatal platform error and notify the gateway supervisor so the existing
+    reconnect watcher can replace the dead adapter.
+    """
+    adapter = DiscordAdapter(PlatformConfig(enabled=True, token="token"))
+    adapter._running = True
+    adapter._ready_event.set()
+    adapter._notify_fatal_error = AsyncMock()
+
+    async def crash():
+        raise ConnectionResetError("Cannot write to closing transport")
+
+    task = asyncio.create_task(crash())
+    await asyncio.sleep(0)
+
+    adapter._handle_bot_task_done(task)
+    await asyncio.sleep(0)
+
+    assert adapter.has_fatal_error is True
+    assert adapter.fatal_error_retryable is True
+    assert adapter.fatal_error_code == "discord_gateway_task_exited"
+    assert adapter.fatal_error_message is not None
+    assert "Cannot write to closing transport" in adapter.fatal_error_message
+    adapter._notify_fatal_error.assert_awaited_once()
+
+
+@pytest.mark.asyncio
+async def test_discord_bot_task_done_ignored_during_intentional_disconnect():
+    adapter = DiscordAdapter(PlatformConfig(enabled=True, token="token"))
+    adapter._running = True
+    adapter._ready_event.set()
+    adapter._disconnecting = True
+    adapter._notify_fatal_error = AsyncMock()
+
+    async def stop_cleanly():
+        return None
+
+    task = asyncio.create_task(stop_cleanly())
+    await asyncio.sleep(0)
+
+    adapter._handle_bot_task_done(task)
+    await asyncio.sleep(0)
+
+    assert adapter.has_fatal_error is False
+    adapter._notify_fatal_error.assert_not_awaited()

tests/plugins/test_langfuse_plugin.py

@@ -171,6 +171,40 @@ class TestHooksInert:
         mod.on_post_tool_call(tool_name="read_file", args={}, result="ok", task_id="t", session_id="s")
 
 
+class TestPayloadSanitization:
+    def test_safe_value_redacts_base64_data_uri_instead_of_truncating(self):
+        sys.modules.pop("plugins.observability.langfuse", None)
+        import importlib
+        mod = importlib.import_module("plugins.observability.langfuse")
+
+        payload = "data:image/png;base64," + ("a" * 20000)
+        result = mod._safe_value(payload)
+
+        assert result == {
+            "type": "data_uri",
+            "media_type": "image/png",
+            "omitted": True,
+            "length": len(payload),
+        }
+
+    def test_serialize_messages_redacts_data_uri_parts(self):
+        sys.modules.pop("plugins.observability.langfuse", None)
+        import importlib
+        mod = importlib.import_module("plugins.observability.langfuse")
+
+        payload = "data:image/jpeg;base64," + ("b" * 20000)
+        serialized = mod._serialize_messages([
+            {"role": "user", "content": [{"type": "image_url", "image_url": {"url": payload}}]}
+        ])
+
+        assert serialized[0]["content"][0]["image_url"]["url"] == {
+            "type": "data_uri",
+            "media_type": "image/jpeg",
+            "omitted": True,
+            "length": len(payload),
+        }
+
+
 # ---------------------------------------------------------------------------
 # Placeholder-credential guard (#23823).
 #
@@ -704,3 +738,76 @@ class TestToolObservationKeying:
         assert ended["output"] == {"status": "done"}
         assert not state.tools
 
+
+class TestUsageFromSanitizedResponse:
+    """Regression: ``post_api_request`` delivers ``response`` as a sanitized
+    dict (no ``.usage`` attribute) plus a separate ``usage`` summary dict. The
+    post-call handler must read the ``usage`` dict instead of treating the dict
+    response as a usage-bearing object and dropping all token/cost data."""
+
+    def _setup(self, mod, monkeypatch):
+        # Active client so on_post_llm_call does not early-return.
+        monkeypatch.setattr(mod, "_get_langfuse", lambda: object())
+        observation = object()
+        state = mod.TraceState(trace_id="trace-1", root_ctx=None, root_span=None)
+        state.generations[mod._request_key(1)] = observation
+        monkeypatch.setitem(mod._TRACE_STATE, mod._trace_key("task-1", "session-1"), state)
+        captured = {}
+
+        def fake_end_observation(obs, *, output=None, metadata=None, usage_details=None, cost_details=None):
+            captured["usage_details"] = usage_details
+
+        monkeypatch.setattr(mod, "_end_observation", fake_end_observation)
+        return captured
+
+    def test_sanitized_dict_response_uses_usage_dict(self, monkeypatch):
+        sys.modules.pop("plugins.observability.langfuse", None)
+        mod = importlib.import_module("plugins.observability.langfuse")
+        captured = self._setup(mod, monkeypatch)
+
+        # A plain dict has no ``.usage`` attribute — mirrors post_api_request.
+        mod.on_post_llm_call(
+            task_id="task-1",
+            session_id="session-1",
+            api_call_count=1,
+            model="gemini-3-flash-preview",
+            response={"model": "gemini-3-flash-preview", "usage": {"input_tokens": 100, "output_tokens": 20}},
+            usage={"input_tokens": 100, "output_tokens": 20},
+            assistant_content_chars=42,
+        )
+
+        # Before the fix the dict response shadowed the usage dict and tokens
+        # were lost (usage_details == {}).
+        assert captured["usage_details"] == {"input": 100, "output": 20}
+
+    def test_real_response_object_with_usage_still_used(self, monkeypatch):
+        sys.modules.pop("plugins.observability.langfuse", None)
+        mod = importlib.import_module("plugins.observability.langfuse")
+        captured = self._setup(mod, monkeypatch)
+
+        # A response object that genuinely carries usage must still take the
+        # response-object path (post_llm_call / legacy behavior).
+        seen = {}
+
+        def fake_usage_and_cost(resp, **_):
+            seen["resp"] = resp
+            return {"input": 7, "output": 3}, {}
+
+        monkeypatch.setattr(mod, "_usage_and_cost", fake_usage_and_cost)
+
+        class _Resp:
+            usage = {"prompt_tokens": 7, "completion_tokens": 3}
+
+        resp = _Resp()
+        mod.on_post_llm_call(
+            task_id="task-1",
+            session_id="session-1",
+            api_call_count=1,
+            model="gemini-3-flash-preview",
+            response=resp,
+            usage={"input_tokens": 999, "output_tokens": 999},
+            assistant_content_chars=42,
+        )
+
+        assert seen["resp"] is resp
+        assert captured["usage_details"] == {"input": 7, "output": 3}

tests/plugins/test_nemo_relay_plugin.py

@@ -2,13 +2,17 @@
 
 from __future__ import annotations
 
+import asyncio
 import builtins
+import gc
 import importlib
 import json
 import sys
+import warnings
 from pathlib import Path
 from types import SimpleNamespace
 
+import pytest
 import yaml
 
 from hermes_cli.plugins import PluginManager
@@ -37,7 +41,7 @@ class _FakeNemoRelay:
             call_end=self._tool_call_end,
             execute=self._tool_execute,
         )
-        self.plugin = SimpleNamespace(initialize=self._plugin_initialize)
+        self.plugin = SimpleNamespace(initialize=self._plugin_initialize, clear=self._plugin_clear)
         self.LLMRequest = _FakeLLMRequest
         self.AtofExporterConfig = _FakeAtofExporterConfig
         self.AtofExporterMode = SimpleNamespace(Append="append", Overwrite="overwrite")
@@ -93,6 +97,9 @@ class _FakeNemoRelay:
         self.events.append(("plugin.initialize", config))
         return {"diagnostics": []}
 
+    async def _plugin_clear(self):
+        self.events.append(("plugin.clear",))
+
 
 class _FakeLLMRequest:
     def __init__(self, headers, content):
@@ -115,6 +122,10 @@ class _FakeAtofExporter:
     def register(self, name):
         self.events.append(("atof.register", name, self.config.output_directory, self.config.filename))
 
+    def deregister(self, name):
+        self.events.append(("atof.deregister", name, self.config.output_directory, self.config.filename))
+        return True
+
 
 class _FakeAtifExporter:
     def __init__(self, events, session_id, agent_name, agent_version, kwargs):
@@ -143,6 +154,33 @@ def _fresh_plugin(monkeypatch, fake):
     return plugin
 
 
+def _wrapped_downstream_error(original):
+    class _DownstreamExecutionError(Exception):
+        def __init__(self, original):
+            super().__init__(str(original))
+            self.original = original
+
+    return _DownstreamExecutionError(original)
+
+
+def _enable_adaptive_plugin(tmp_path, monkeypatch) -> None:
+    plugins_toml = tmp_path / "plugins.toml"
+    plugins_toml.write_text(
+        """
+version = 1
+
+[[components]]
+kind = "adaptive"
+enabled = true
+
+[components.config.tool_parallelism]
+mode = "observe_only"
+""",
+        encoding="utf-8",
+    )
+    monkeypatch.setenv("HERMES_NEMO_RELAY_PLUGINS_TOML", str(plugins_toml))
+
+
 def test_manifest_fields():
     data = yaml.safe_load((PLUGIN_DIR / "plugin.yaml").read_text())
     assert data["name"] == "nemo_relay"
@@ -445,6 +483,252 @@ output_directory = "{atif_dir}"
     assert atif_dir.is_dir()
 
 
+def test_nemo_relay_plugin_clears_plugins_toml_on_final_session_finalize_and_reinitializes(tmp_path, monkeypatch):
+    fake = _FakeNemoRelay()
+    plugin = _fresh_plugin(monkeypatch, fake)
+    plugins_toml = tmp_path / "plugins.toml"
+    plugins_toml.write_text(
+        """
+version = 1
+
+[[components]]
+kind = "observability"
+enabled = true
+""",
+        encoding="utf-8",
+    )
+    monkeypatch.setenv("HERMES_NEMO_RELAY_PLUGINS_TOML", str(plugins_toml))
+
+    plugin.on_session_start(session_id="s1")
+    plugin.on_session_finalize(session_id="s1", reason="shutdown")
+    plugin.on_session_start(session_id="s2")
+
+    event_names = [event[0] for event in fake.events]
+    assert event_names.count("plugin.initialize") == 2
+    assert event_names.count("plugin.clear") == 1
+
+
+def test_nemo_relay_plugin_keeps_plugins_toml_active_while_other_sessions_remain(tmp_path, monkeypatch):
+    fake = _FakeNemoRelay()
+    plugin = _fresh_plugin(monkeypatch, fake)
+    plugins_toml = tmp_path / "plugins.toml"
+    plugins_toml.write_text(
+        """
+version = 1
+
+[[components]]
+kind = "observability"
+enabled = true
+""",
+        encoding="utf-8",
+    )
+    monkeypatch.setenv("HERMES_NEMO_RELAY_PLUGINS_TOML", str(plugins_toml))
+
+    plugin.on_session_start(session_id="parent")
+    plugin.on_session_start(session_id="child")
+    plugin.on_session_finalize(session_id="child", reason="shutdown")
+    plugin.on_session_finalize(session_id="parent", reason="shutdown")
+
+    event_names = [event[0] for event in fake.events]
+    assert event_names.count("plugin.initialize") == 1
+    assert event_names.count("plugin.clear") == 1
+
+
+def test_nemo_relay_plugin_reinitializes_plugins_toml_inside_active_event_loop(tmp_path, monkeypatch):
+    fake = _FakeNemoRelay()
+    plugin = _fresh_plugin(monkeypatch, fake)
+    plugins_toml = tmp_path / "plugins.toml"
+    plugins_toml.write_text(
+        """
+version = 1
+
+[[components]]
+kind = "observability"
+enabled = true
+""",
+        encoding="utf-8",
+    )
+    monkeypatch.setenv("HERMES_NEMO_RELAY_PLUGINS_TOML", str(plugins_toml))
+
+    async def _drive() -> None:
+        plugin.on_session_start(session_id="s1")
+        plugin.on_session_finalize(session_id="s1", reason="shutdown")
+        plugin.on_session_start(session_id="s2")
+        await asyncio.sleep(0)
+
+    with warnings.catch_warnings(record=True) as caught:
+        warnings.simplefilter("always")
+        asyncio.run(_drive())
+        gc.collect()
+
+    assert not any("was never awaited" in str(w.message) for w in caught)
+    runtime = plugin._get_runtime()
+    assert runtime is not None
+    assert runtime._plugin_config_initialized is True
+    scope_push_names = [event[1] for event in fake.events if event[0] == "scope.push"]
+    assert "hermes-session-s2" in scope_push_names
+
+
+def test_nemo_relay_plugin_retries_plugins_toml_after_clear_failure(tmp_path, monkeypatch):
+    fake = _FakeNemoRelay()
+    initialize_calls = 0
+
+    async def _counting_initialize(config):
+        nonlocal initialize_calls
+        initialize_calls += 1
+        fake.events.append(("plugin.initialize.attempt", initialize_calls, config))
+        return {"diagnostics": []}
+
+    async def _failing_clear():
+        fake.events.append(("plugin.clear.failed",))
+        raise RuntimeError("boom")
+
+    fake.plugin.initialize = _counting_initialize
+    fake.plugin.clear = _failing_clear
+    plugin = _fresh_plugin(monkeypatch, fake)
+    plugins_toml = tmp_path / "plugins.toml"
+    plugins_toml.write_text(
+        """
+version = 1
+
+[[components]]
+kind = "observability"
+enabled = true
+""",
+        encoding="utf-8",
+    )
+    monkeypatch.setenv("HERMES_NEMO_RELAY_PLUGINS_TOML", str(plugins_toml))
+
+    plugin.on_session_start(session_id="s1")
+    plugin.on_session_finalize(session_id="s1", reason="shutdown")
+    plugin.on_session_start(session_id="s2")
+
+    event_names = [event[0] for event in fake.events]
+    assert event_names.count("plugin.initialize.attempt") == 2
+    assert event_names.count("plugin.clear.failed") == 1
+    scope_push_names = [event[1] for event in fake.events if event[0] == "scope.push"]
+    assert "hermes-session-s2" in scope_push_names
+
+
+def test_nemo_relay_plugin_disables_direct_atif_when_plugins_toml_owns_atif(tmp_path, monkeypatch):
+    fake = _FakeNemoRelay()
+    plugin = _fresh_plugin(monkeypatch, fake)
+    plugins_toml = tmp_path / "plugins.toml"
+    plugins_toml.write_text(
+        f"""
+version = 1
+
+[[components]]
+kind = "observability"
+enabled = true
+
+[components.config.atif]
+enabled = true
+output_directory = "{(tmp_path / "managed-atif").as_posix()}"
+""",
+        encoding="utf-8",
+    )
+    monkeypatch.setenv("HERMES_NEMO_RELAY_PLUGINS_TOML", str(plugins_toml))
+    monkeypatch.setenv("HERMES_NEMO_RELAY_ATIF_ENABLED", "1")
+    monkeypatch.setenv("HERMES_NEMO_RELAY_ATIF_OUTPUT_DIRECTORY", str(tmp_path / "direct-atif"))
+
+    plugin.on_session_start(session_id="s1")
+    plugin.on_session_finalize(session_id="s1", reason="shutdown")
+
+    event_names = [event[0] for event in fake.events]
+    assert "plugin.initialize" in event_names
+    assert "plugin.clear" in event_names
+    assert "atif.register" not in event_names
+    assert not (tmp_path / "direct-atif" / "hermes-atif-s1.json").exists()
+
+
+def test_nemo_relay_plugin_keeps_direct_atif_when_plugins_toml_init_fails(tmp_path, monkeypatch):
+    fake = _FakeNemoRelay()
+
+    async def _failing_initialize(config):
+        fake.events.append(("plugin.initialize.failed", config))
+        raise RuntimeError("boom")
+
+    fake.plugin.initialize = _failing_initialize
+    plugin = _fresh_plugin(monkeypatch, fake)
+    plugins_toml = tmp_path / "plugins.toml"
+    plugins_toml.write_text(
+        f"""
+version = 1
+
+[[components]]
+kind = "observability"
+enabled = true
+
+[components.config.atif]
+enabled = true
+output_directory = "{(tmp_path / "managed-atif").as_posix()}"
+""",
+        encoding="utf-8",
+    )
+    monkeypatch.setenv("HERMES_NEMO_RELAY_PLUGINS_TOML", str(plugins_toml))
+    monkeypatch.setenv("HERMES_NEMO_RELAY_ATIF_ENABLED", "1")
+    monkeypatch.setenv("HERMES_NEMO_RELAY_ATIF_OUTPUT_DIRECTORY", str(tmp_path / "direct-atif"))
+
+    plugin.on_session_start(session_id="s1")
+    plugin.on_session_finalize(session_id="s1", reason="shutdown")
+
+    event_names = [event[0] for event in fake.events]
+    assert "plugin.initialize.failed" in event_names
+    assert "plugin.clear" not in event_names
+    assert "atif.register" in event_names
+    assert (tmp_path / "direct-atif" / "hermes-atif-s1.json").exists()
+
+
+def test_nemo_relay_plugin_retries_plugins_toml_after_fallback_only_session_and_clears_direct_atof(
+    tmp_path,
+    monkeypatch,
+):
+    fake = _FakeNemoRelay()
+    initialize_calls = 0
+
+    async def _flaky_initialize(config):
+        nonlocal initialize_calls
+        initialize_calls += 1
+        fake.events.append(("plugin.initialize.attempt", initialize_calls, config))
+        if initialize_calls == 1:
+            raise RuntimeError("boom")
+        return {"diagnostics": []}
+
+    fake.plugin.initialize = _flaky_initialize
+    plugin = _fresh_plugin(monkeypatch, fake)
+    plugins_toml = tmp_path / "plugins.toml"
+    plugins_toml.write_text(
+        f"""
+version = 1
+
+[[components]]
+kind = "observability"
+enabled = true
+
+[components.config.atof]
+enabled = true
+output_directory = "{(tmp_path / "managed-atof").as_posix()}"
+""",
+        encoding="utf-8",
+    )
+    monkeypatch.setenv("HERMES_NEMO_RELAY_PLUGINS_TOML", str(plugins_toml))
+    monkeypatch.setenv("HERMES_NEMO_RELAY_ATOF_ENABLED", "1")
+    monkeypatch.setenv("HERMES_NEMO_RELAY_ATOF_OUTPUT_DIRECTORY", str(tmp_path / "direct-atof"))
+
+    plugin.on_session_start(session_id="s1")
+    plugin.on_session_finalize(session_id="s1", reason="shutdown")
+    plugin.on_session_start(session_id="s2")
+
+    runtime = plugin._get_runtime()
+    assert runtime is not None
+    assert runtime._plugin_config_initialized is True
+    event_names = [event[0] for event in fake.events]
+    assert event_names.count("plugin.initialize.attempt") == 2
+    assert event_names.count("atof.register") == 1
+    assert event_names.count("atof.deregister") == 1
+
+
 def test_nemo_relay_adaptive_llm_execution_middleware_preserves_raw_response(tmp_path, monkeypatch):
     fake = _FakeNemoRelay()
     plugin = _fresh_plugin(monkeypatch, fake)
@@ -457,8 +741,8 @@ version = 1
 kind = "adaptive"
 enabled = true
 
-[components.config]
-mode = "route"
+[components.config.tool_parallelism]
+mode = "observe_only"
 """,
         encoding="utf-8",
     )
@@ -506,7 +790,7 @@ mode = "route"
     assert response.choices == [raw_choice]
     assert seen_request["intercepted"] is True
     execute_start = next(event for event in fake.events if event[0] == "llm.execute.start")
-    assert execute_start[3]["data"]["mode"] == "route"
+    assert execute_start[3]["data"]["mode"] == "observe_only"
     execute_end = next(event for event in fake.events if event[0] == "llm.execute.end")
     assert execute_end[2] == {
         "model": "demo-model",
@@ -527,6 +811,298 @@ mode = "route"
     }
 
 
+def test_nemo_relay_adaptive_llm_execution_preserves_downstream_error(tmp_path, monkeypatch):
+    fake = _FakeNemoRelay()
+
+    def native_like_execute(name, request, func, **kwargs):
+        fake.events.append(("llm.execute.start", name, request.content, kwargs))
+        try:
+            return func(_FakeLLMRequest(request.headers, {"intercepted": True, **request.content}))
+        except Exception as exc:
+            raise RuntimeError(f"internal error: {type(exc).__name__}: {exc}") from None
+
+    fake.llm.execute = native_like_execute
+    plugin = _fresh_plugin(monkeypatch, fake)
+    _enable_adaptive_plugin(tmp_path, monkeypatch)
+
+    class ProviderAuthError(Exception):
+        status_code = 403
+
+    provider_error = ProviderAuthError("provider auth failed")
+
+    def next_call(request):
+        raise _wrapped_downstream_error(provider_error)
+
+    with pytest.raises(ProviderAuthError) as caught:
+        plugin.on_llm_execution_middleware(
+            session_id="s1",
+            provider="anthropic",
+            model="demo-model",
+            request={"messages": [{"role": "user", "content": "hi"}]},
+            next_call=next_call,
+        )
+
+    assert caught.value is provider_error
+    assert caught.value.status_code == 403
+
+
+def test_nemo_relay_adaptive_llm_execution_preserves_downstream_error_with_relay_suffix(
+    tmp_path, monkeypatch
+):
+    # Guards the startswith (vs exact ==) match in _is_relay_wrapped_callback_error:
+    # Relay re-wraps the callback failure with its canonical prefix but APPENDS a
+    # trailing suffix. Exact equality would miss this and surface Relay's wrapper;
+    # prefix matching must still recover the original downstream error.
+    fake = _FakeNemoRelay()
+
+    def native_like_execute(name, request, func, **kwargs):
+        try:
+            return func(_FakeLLMRequest(request.headers, {"intercepted": True, **request.content}))
+        except Exception as exc:
+            raise RuntimeError(f"internal error: {type(exc).__name__}: {exc} (retried 3x)") from None
+
+    fake.llm.execute = native_like_execute
+    plugin = _fresh_plugin(monkeypatch, fake)
+    _enable_adaptive_plugin(tmp_path, monkeypatch)
+
+    class ProviderAuthError(Exception):
+        status_code = 403
+
+    provider_error = ProviderAuthError("provider auth failed")
+
+    def next_call(request):
+        raise _wrapped_downstream_error(provider_error)
+
+    with pytest.raises(ProviderAuthError) as caught:
+        plugin.on_llm_execution_middleware(
+            session_id="s1",
+            provider="anthropic",
+            model="demo-model",
+            request={"messages": [{"role": "user", "content": "hi"}]},
+            next_call=next_call,
+        )
+
+    assert caught.value is provider_error
+    assert caught.value.status_code == 403
+
+
+def test_nemo_relay_adaptive_llm_execution_keeps_unrelated_internal_error(tmp_path, monkeypatch):
+    fake = _FakeNemoRelay()
+
+    relay_error = RuntimeError("internal error: relay setup failed")
+
+    def internal_error_execute(name, request, func, **kwargs):
+        raise relay_error
+
+    fake.llm.execute = internal_error_execute
+    plugin = _fresh_plugin(monkeypatch, fake)
+    _enable_adaptive_plugin(tmp_path, monkeypatch)
+
+    with pytest.raises(RuntimeError) as caught:
+        plugin.on_llm_execution_middleware(
+            session_id="s1",
+            provider="anthropic",
+            model="demo-model",
+            request={"messages": [{"role": "user", "content": "hi"}]},
+            next_call=lambda request: {"raw": request},
+        )
+
+    assert caught.value is relay_error
+
+
+def test_nemo_relay_adaptive_llm_execution_keeps_wrapped_relay_error_after_downstream_failure(
+    tmp_path, monkeypatch
+):
+    fake = _FakeNemoRelay()
+    relay_error = RuntimeError("internal error: RuntimeError: relay policy blocked after downstream")
+
+    def translated_execute(name, request, func, **kwargs):
+        try:
+            return func(_FakeLLMRequest(request.headers, {"intercepted": True, **request.content}))
+        except Exception:
+            raise relay_error
+
+    fake.llm.execute = translated_execute
+    plugin = _fresh_plugin(monkeypatch, fake)
+    _enable_adaptive_plugin(tmp_path, monkeypatch)
+
+    def next_call(request):
+        raise _wrapped_downstream_error(RuntimeError("provider failed"))
+
+    with pytest.raises(RuntimeError) as caught:
+        plugin.on_llm_execution_middleware(
+            session_id="s1",
+            provider="anthropic",
+            model="demo-model",
+            request={"messages": [{"role": "user", "content": "hi"}]},
+            next_call=next_call,
+        )
+
+    assert caught.value is relay_error
+
+
+def test_nemo_relay_adaptive_llm_execution_keeps_relay_translated_error(tmp_path, monkeypatch):
+    fake = _FakeNemoRelay()
+
+    class RelayPolicyError(Exception):
+        pass
+
+    relay_error = RelayPolicyError("relay policy blocked")
+
+    def translated_execute(name, request, func, **kwargs):
+        try:
+            return func(_FakeLLMRequest(request.headers, {"intercepted": True, **request.content}))
+        except Exception:
+            raise relay_error
+
+    fake.llm.execute = translated_execute
+    plugin = _fresh_plugin(monkeypatch, fake)
+    _enable_adaptive_plugin(tmp_path, monkeypatch)
+
+    provider_error = RuntimeError("provider failed")
+
+    def next_call(request):
+        raise _wrapped_downstream_error(provider_error)
+
+    with pytest.raises(RelayPolicyError) as caught:
+        plugin.on_llm_execution_middleware(
+            session_id="s1",
+            provider="anthropic",
+            model="demo-model",
+            request={"messages": [{"role": "user", "content": "hi"}]},
+            next_call=next_call,
+        )
+
+    assert caught.value is relay_error
+
+
+def test_nemo_relay_downstream_unwrap_matches_real_middleware_wrapper_shape(monkeypatch):
+    # Regression guard against core/plugin drift. The synthetic tests above model
+    # the downstream-error wrapper with a local class, so they keep passing even
+    # if core middleware renames its private ``_DownstreamExecutionError`` or drops
+    # ``.original`` -- the exact shape the plugin matches by name at
+    # ``_original_downstream_error``. Capture the wrapper the REAL
+    # ``hermes_cli.middleware._run_execution_chain`` hands to a middleware
+    # callback's ``next_call`` and assert the plugin's detector unwraps it to the
+    # original exception. If core middleware changes the wrapper shape, this fails
+    # here instead of silently defeating the unwrap in production.
+    from hermes_cli import middleware
+
+    from plugins.observability.nemo_relay import _original_downstream_error
+
+    class ProviderError(Exception):
+        status_code = 403
+
+    provider_error = ProviderError("provider auth failed")
+    captured: dict[str, Exception] = {}
+
+    def terminal_call(payload):
+        raise provider_error
+
+    def capturing_callback(**kwargs):
+        next_call = kwargs["next_call"]
+        try:
+            return next_call(kwargs.get("request"))
+        except Exception as exc:
+            captured["wrapper"] = exc
+            # Surface the original so the chain unwinds without re-wrapping noise.
+            raise _original_downstream_error(exc) from None
+
+    with pytest.raises(ProviderError) as caught:
+        middleware._run_execution_chain(
+            "llm",
+            [capturing_callback],
+            terminal_call,
+            request={"messages": []},
+        )
+
+    wrapper = captured["wrapper"]
+    # The wrapper the plugin sees must match what _original_downstream_error keys on.
+    assert wrapper.__class__.__name__ == "_DownstreamExecutionError"
+    assert isinstance(getattr(wrapper, "original", None), BaseException)
+    assert _original_downstream_error(wrapper) is provider_error
+    assert caught.value is provider_error
+    assert caught.value.status_code == 403
+
+
+def _adaptive_llm_execute_mode(tmp_path, monkeypatch, plugins_toml_text: str) -> str:
+    fake = _FakeNemoRelay()
+    plugin = _fresh_plugin(monkeypatch, fake)
+    plugins_toml = tmp_path / "plugins.toml"
+    plugins_toml.write_text(plugins_toml_text, encoding="utf-8")
+    monkeypatch.setenv("HERMES_NEMO_RELAY_PLUGINS_TOML", str(plugins_toml))
+
+    plugin.on_llm_execution_middleware(
+        session_id="s1",
+        provider="anthropic",
+        model="demo-model",
+        request={"messages": [{"role": "user", "content": "hi"}]},
+        next_call=lambda request: {"raw": request},
+    )
+
+    execute_start = next(event for event in fake.events if event[0] == "llm.execute.start")
+    return execute_start[3]["data"]["mode"]
+
+
+def test_nemo_relay_adaptive_llm_execution_middleware_defaults_to_observe_only_when_mode_is_unset(
+    tmp_path, monkeypatch
+):
+    mode = _adaptive_llm_execute_mode(
+        tmp_path,
+        monkeypatch,
+        """
+version = 1
+
+[[components]]
+kind = "adaptive"
+enabled = true
+
+[components.config]
+version = 1
+""",
+    )
+    assert mode == "observe_only"
+
+
+def test_nemo_relay_adaptive_llm_execution_middleware_accepts_legacy_top_level_mode(tmp_path, monkeypatch):
+    mode = _adaptive_llm_execute_mode(
+        tmp_path,
+        monkeypatch,
+        """
+version = 1
+
+[[components]]
+kind = "adaptive"
+enabled = true
+
+[components.config]
+mode = "route"
+""",
+    )
+    assert mode == "route"
+
+
+def test_nemo_relay_adaptive_llm_execution_middleware_prefers_tool_parallelism_mode(tmp_path, monkeypatch):
+    mode = _adaptive_llm_execute_mode(
+        tmp_path,
+        monkeypatch,
+        """
+version = 1
+
+[[components]]
+kind = "adaptive"
+enabled = true
+
+[components.config]
+mode = "route"
+
+[components.config.tool_parallelism]
+mode = "schedule"
+""",
+    )
+    assert mode == "schedule"
+
+
 def test_nemo_relay_llm_execution_middleware_calls_through_without_adaptive(monkeypatch):
     fake = _FakeNemoRelay()
     plugin = _fresh_plugin(monkeypatch, fake)
@@ -555,8 +1131,8 @@ version = 1
 kind = "adaptive"
 enabled = true
 
-[components.config]
-mode = "route"
+[components.config.tool_parallelism]
+mode = "observe_only"
 """,
         encoding="utf-8",
     )
@@ -582,10 +1158,131 @@ mode = "route"
     assert response == {"raw": True, "args": {"command": "pwd", "intercepted": True}}
     assert seen_args["intercepted"] is True
     execute_start = next(event for event in fake.events if event[0] == "tool.execute.start")
-    assert execute_start[3]["data"]["mode"] == "route"
+    assert execute_start[3]["data"]["mode"] == "observe_only"
     assert execute_start[3]["data"]["tool_call_id"] == "tool-1"
 
 
+def test_nemo_relay_adaptive_tool_execution_preserves_downstream_error(tmp_path, monkeypatch):
+    fake = _FakeNemoRelay()
+
+    def native_like_execute(name, args, func, **kwargs):
+        fake.events.append(("tool.execute.start", name, args, kwargs))
+        try:
+            return func({"intercepted": True, **args})
+        except Exception as exc:
+            raise RuntimeError(f"internal error: {type(exc).__name__}: {exc}") from None
+
+    fake.tools.execute = native_like_execute
+    plugin = _fresh_plugin(monkeypatch, fake)
+    _enable_adaptive_plugin(tmp_path, monkeypatch)
+
+    class ToolAuthError(Exception):
+        status_code = 403
+
+    tool_error = ToolAuthError("tool auth failed")
+
+    def next_call(args):
+        raise _wrapped_downstream_error(tool_error)
+
+    with pytest.raises(ToolAuthError) as caught:
+        plugin.on_tool_execution_middleware(
+            session_id="s1",
+            tool_name="terminal",
+            args={"command": "pwd"},
+            next_call=next_call,
+        )
+
+    assert caught.value is tool_error
+    assert caught.value.status_code == 403
+
+
+def test_nemo_relay_adaptive_tool_execution_keeps_unrelated_internal_error(tmp_path, monkeypatch):
+    fake = _FakeNemoRelay()
+
+    relay_error = RuntimeError("internal error: relay setup failed")
+
+    def internal_error_execute(name, args, func, **kwargs):
+        raise relay_error
+
+    fake.tools.execute = internal_error_execute
+    plugin = _fresh_plugin(monkeypatch, fake)
+    _enable_adaptive_plugin(tmp_path, monkeypatch)
+
+    with pytest.raises(RuntimeError) as caught:
+        plugin.on_tool_execution_middleware(
+            session_id="s1",
+            tool_name="terminal",
+            args={"command": "pwd"},
+            next_call=lambda args: {"raw": args},
+        )
+
+    assert caught.value is relay_error
+
+
+def test_nemo_relay_adaptive_tool_execution_keeps_wrapped_relay_error_after_downstream_failure(
+    tmp_path, monkeypatch
+):
+    fake = _FakeNemoRelay()
+    relay_error = RuntimeError("internal error: RuntimeError: relay policy blocked after downstream")
+
+    def translated_execute(name, args, func, **kwargs):
+        try:
+            return func({"intercepted": True, **args})
+        except Exception:
+            raise relay_error
+
+    fake.tools.execute = translated_execute
+    plugin = _fresh_plugin(monkeypatch, fake)
+    _enable_adaptive_plugin(tmp_path, monkeypatch)
+
+    def next_call(args):
+        raise _wrapped_downstream_error(RuntimeError("tool failed"))
+
+    with pytest.raises(RuntimeError) as caught:
+        plugin.on_tool_execution_middleware(
+            session_id="s1",
+            tool_name="terminal",
+            args={"command": "pwd"},
+            next_call=next_call,
+        )
+
+    assert caught.value is relay_error
+
+
+def test_nemo_relay_adaptive_tool_execution_keeps_relay_translated_error(tmp_path, monkeypatch):
+    fake = _FakeNemoRelay()
+
+    class RelayPolicyError(Exception):
+        pass
+
+    relay_error = RelayPolicyError("relay policy blocked")
+
+    def translated_execute(name, args, func, **kwargs):
+        try:
+            return func({"intercepted": True, **args})
+        except Exception:
+            raise relay_error
+
+    fake.tools.execute = translated_execute
+    plugin = _fresh_plugin(monkeypatch, fake)
+    _enable_adaptive_plugin(tmp_path, monkeypatch)
+
+    tool_error = RuntimeError("tool failed")
+
+    def next_call(args):
+        raise _wrapped_downstream_error(tool_error)
+
+    with pytest.raises(RelayPolicyError) as caught:
+        plugin.on_tool_execution_middleware(
+            session_id="s1",
+            tool_name="terminal",
+            args={"command": "pwd"},
+            next_call=next_call,
+        )
+
+    assert caught.value is relay_error
+
+
 def test_nemo_relay_tool_execution_middleware_calls_through_without_adaptive(monkeypatch):
     fake = _FakeNemoRelay()
     plugin = _fresh_plugin(monkeypatch, fake)
@@ -613,8 +1310,8 @@ version = 1
 kind = "adaptive"
 enabled = true
 
-[components.config]
-mode = "route"
+[components.config.tool_parallelism]
+mode = "observe_only"
 """,
         encoding="utf-8",
     )

tests/plugins/web/test_parallel_keyless_mcp.py

@@ -0,0 +1,383 @@
+"""Keyless Parallel search via the free hosted Search MCP.
+
+Covers the transport added in ``plugins/web/parallel/provider.py`` that lets
+``web_search`` work with no ``PARALLEL_API_KEY``:
+
+- ``_mcp_headers``  — Bearer attached only when a key is held
+- ``_decode_mcp_envelope`` — plain-JSON and SSE (``data:``) response bodies
+- ``_mcp_payload`` — structuredContent preferred, text-block JSON fallback, errors
+- ``_mcp_web_search`` — full handshake (mocked transport) → standard search shape
+- ``ParallelWebSearchProvider.search`` — keyless path routes to the MCP
+"""
+
+from __future__ import annotations
+
+import asyncio
+import json
+from unittest.mock import patch
+
+import pytest
+
+import plugins.web.parallel.provider as pp
+
+
+# ─── _mcp_headers ──────────────────────────────────────────────────────────
+
+class TestMcpHeaders:
+    def test_anonymous_has_no_authorization(self):
+        h = pp._mcp_headers(session_id=None, api_key=None)
+        assert "Authorization" not in h
+        assert h["Accept"] == "application/json, text/event-stream"
+        assert "Mcp-Session-Id" not in h
+
+    def test_user_agent_is_generic_not_hermes(self):
+        # Telemetry policy: no third-party usage attribution without opt-in.
+        # The UA must be set (not python-httpx default) but must not name
+        # hermes, on both the anonymous and keyed paths.
+        for ua in (
+            pp._mcp_headers(session_id=None, api_key=None)["User-Agent"],
+            pp._mcp_headers(session_id="sid", api_key="pk-live")["User-Agent"],
+        ):
+            assert ua == f"{pp._MCP_CLIENT_NAME}/{pp._MCP_CLIENT_VERSION}"
+            assert "hermes" not in ua.lower()
+
+    def test_session_id_and_bearer_when_present(self):
+        h = pp._mcp_headers(session_id="sid-123", api_key="pk-live")
+        assert h["Mcp-Session-Id"] == "sid-123"
+        assert h["Authorization"] == "Bearer pk-live"
+
+
+# ─── SSE / JSON-RPC parsing ──────────────────────────────────────────────────
+
+class TestMcpResponseParsing:
+    def test_plain_json_matched_by_id(self):
+        body = '{"jsonrpc":"2.0","id":"abc","result":{"ok":true}}'
+        assert pp._mcp_response_envelope(body, "abc")["result"]["ok"] is True
+
+    def test_sse_selects_response_for_request_id_skipping_notifications(self):
+        # A progress notification (no id) precedes the real result; an unrelated
+        # response id is also present. We must pick the one matching our id.
+        body = (
+            'event: message\ndata: {"jsonrpc":"2.0","method":"notifications/progress","params":{"p":1}}\n\n'
+            'event: message\ndata: {"jsonrpc":"2.0","id":"other","result":{"ok":false}}\n\n'
+            'event: message\ndata: {"jsonrpc":"2.0","id":"req-1","result":{"ok":true}}\n\n'
+        )
+        env = pp._mcp_response_envelope(body, "req-1")
+        assert env["result"]["ok"] is True
+
+    def test_sse_multiline_data_concatenated(self):
+        body = 'data: {"jsonrpc":"2.0","id":"x",\ndata: "result":{"n":42}}\n\n'
+        assert pp._mcp_response_envelope(body, "x")["result"]["n"] == 42
+
+    def test_falls_back_to_last_result_when_id_absent(self):
+        body = '{"jsonrpc":"2.0","id":"server-chose","result":{"ok":true}}'
+        # request id doesn't match, but there's a single result → use it
+        assert pp._mcp_response_envelope(body, "mismatch")["result"]["ok"] is True
+
+    def test_empty_body(self):
+        assert pp._mcp_response_envelope("", "x") == {}
+        assert pp._mcp_response_envelope("   ", "x") == {}
+
+    def test_batched_json_array_flattened(self):
+        # Streamable HTTP may batch messages into a JSON array.
+        body = ('[{"jsonrpc":"2.0","method":"notifications/progress"},'
+                '{"jsonrpc":"2.0","id":"req-9","result":{"ok":true}}]')
+        assert pp._mcp_response_envelope(body, "req-9")["result"]["ok"] is True
+
+    def test_batched_sse_data_array_flattened(self):
+        body = 'data: [{"jsonrpc":"2.0","id":"a","result":{"n":1}}]\n\n'
+        assert pp._mcp_response_envelope(body, "a")["result"]["n"] == 1
+
+
+# ─── _mcp_payload ────────────────────────────────────────────────────────────
+
+class TestMcpPayload:
+    def test_prefers_structured_content(self):
+        env = {"result": {"structuredContent": {"results": [{"url": "u"}]},
+                          "content": [{"type": "text", "text": "ignored"}]}}
+        assert pp._mcp_payload(env) == {"results": [{"url": "u"}]}
+
+    def test_parses_text_block_json(self):
+        inner = {"search_id": "s1", "results": [{"url": "u", "title": "t"}]}
+        env = {"result": {"content": [{"type": "text", "text": json.dumps(inner)}]}}
+        assert pp._mcp_payload(env)["search_id"] == "s1"
+
+    def test_raises_on_jsonrpc_error(self):
+        with pytest.raises(RuntimeError, match="Parallel MCP error"):
+            pp._mcp_payload({"error": {"code": -32000, "message": "boom"}})
+
+    def test_raises_on_tool_iserror(self):
+        with pytest.raises(RuntimeError, match="Parallel MCP tool error"):
+            pp._mcp_payload({"result": {"isError": True, "content": []}})
+
+
+# ─── _mcp_web_search (mocked transport) ──────────────────────────────────────
+
+class _FakeResponse:
+    def __init__(self, *, text="", headers=None):
+        self.text = text
+        self.headers = headers or {}
+
+    def raise_for_status(self):
+        return None
+
+
+class _FakeClient:
+    """Stands in for httpx.Client: replays init → ack → tools/call."""
+
+    def __init__(self, search_payload, init_session_id="server-sid"):
+        self._search_payload = search_payload
+        self._init_session_id = init_session_id
+        self.calls = []
+
+    def __enter__(self):
+        return self
+
+    def __exit__(self, *exc):
+        return False
+
+    def post(self, url, headers=None, json=None):
+        self.calls.append({"headers": headers, "json": json})
+        req = json or {}
+        method = req.get("method")
+        req_id = req.get("id")
+        if method == "initialize":
+            # Echo the request id, as the real server does.
+            return _FakeResponse(
+                text=json_dumps({"jsonrpc": "2.0", "id": req_id,
+                                 "result": {"protocolVersion": "2099-01-01"}}),
+                headers=(
+                    {"mcp-session-id": self._init_session_id}
+                    if self._init_session_id is not None
+                    else {}
+                ),
+            )
+        if method == "notifications/initialized":
+            return _FakeResponse(text="")
+        # tools/call
+        envelope = {"jsonrpc": "2.0", "id": req_id, "result": {
+            "content": [{"type": "text", "text": json_dumps(self._search_payload)}],
+        }}
+        return _FakeResponse(text=json_dumps(envelope))
+
+
+def json_dumps(obj):
+    return json.dumps(obj)
+
+
+class TestMcpWebSearch:
+    def _payload(self, n):
+        return {"search_id": "s", "results": [
+            {"url": f"https://ex/{i}", "title": f"t{i}",
+             "excerpts": [f"a{i}", f"b{i}"]}
+            for i in range(n)
+        ]}
+
+    def test_returns_standard_shape_and_handshake(self):
+        fake = _FakeClient(self._payload(3))
+        with patch.object(pp.httpx, "Client", return_value=fake):
+            out = pp._mcp_web_search("hello", limit=5, api_key=None)
+
+        assert out["success"] is True
+        # Free-tier results credit Parallel.
+        assert "Parallel" in out["attribution"]
+        web = out["data"]["web"]
+        assert [r["position"] for r in web] == [1, 2, 3]
+        assert web[0]["url"] == "https://ex/0"
+        assert web[0]["description"] == "a0 b0"  # excerpts joined
+        # handshake order
+        methods = [c["json"].get("method") for c in fake.calls]
+        assert methods == ["initialize", "notifications/initialized", "tools/call"]
+        # session id from the initialize response header is reused
+        assert fake.calls[-1]["headers"]["Mcp-Session-Id"] == "server-sid"
+
+    def test_stateless_server_no_session_header_not_invented(self):
+        # A stateless Streamable-HTTP server may omit mcp-session-id on
+        # initialize; we must NOT invent one (sending an unissued session id can
+        # get follow-up requests rejected). The follow-ups carry no header.
+        fake = _FakeClient(self._payload(1), init_session_id=None)
+        with patch.object(pp.httpx, "Client", return_value=fake):
+            out = pp._mcp_web_search("hello", limit=5, api_key=None)
+        assert out["success"] is True
+        follow_ups = [c for c in fake.calls if c["json"].get("method") != "initialize"]
+        assert follow_ups, "expected notifications/initialized + tools/call"
+        assert all("Mcp-Session-Id" not in c["headers"] for c in follow_ups)
+        # anonymous → no Authorization on any call
+        assert all("Authorization" not in c["headers"] for c in fake.calls)
+        # tools/call mirrors query into objective + search_queries
+        args = fake.calls[-1]["json"]["params"]["arguments"]
+        assert args["objective"] == "hello"
+        assert args["search_queries"] == ["hello"]
+
+    def test_limit_is_applied_client_side(self):
+        fake = _FakeClient(self._payload(10))
+        with patch.object(pp.httpx, "Client", return_value=fake):
+            out = pp._mcp_web_search("q", limit=2, api_key=None)
+        assert len(out["data"]["web"]) == 2
+
+    def test_bearer_attached_when_key_present(self):
+        fake = _FakeClient(self._payload(1))
+        with patch.object(pp.httpx, "Client", return_value=fake):
+            pp._mcp_web_search("q", limit=1, api_key="pk-live")
+        assert all(c["headers"]["Authorization"] == "Bearer pk-live" for c in fake.calls)
+
+    def test_negotiated_protocol_version_echoed_post_init(self):
+        fake = _FakeClient(self._payload(1))
+        with patch.object(pp.httpx, "Client", return_value=fake):
+            pp._mcp_web_search("q", limit=1, api_key=None)
+        # initialize request doesn't carry the (not-yet-negotiated) version...
+        assert "MCP-Protocol-Version" not in fake.calls[0]["headers"]
+        # ...but notifications/initialized and tools/call echo the negotiated one.
+        assert fake.calls[1]["headers"]["MCP-Protocol-Version"] == "2099-01-01"
+        assert fake.calls[-1]["headers"]["MCP-Protocol-Version"] == "2099-01-01"
+
+
+# ─── provider.search keyless routing ─────────────────────────────────────────
+
+class TestProviderKeylessSearch:
+    def test_search_without_key_uses_mcp(self, monkeypatch):
+        monkeypatch.delenv("PARALLEL_API_KEY", raising=False)
+        captured = {}
+
+        def _fake(query, limit, api_key):
+            captured.update(query=query, limit=limit, api_key=api_key)
+            return {"success": True, "data": {"web": []}}
+
+        monkeypatch.setattr(pp, "_mcp_web_search", _fake)
+        out = pp.ParallelWebSearchProvider().search("kittens", limit=4)
+        assert out["success"] is True
+        assert captured == {"query": "kittens", "limit": 4, "api_key": None}
+
+    def test_is_available_reflects_key(self, monkeypatch):
+        # is_available() gates the registry's active-provider walk + picker, so
+        # it's key-based (keyless dispatch is handled by _get_backend, not this).
+        monkeypatch.delenv("PARALLEL_API_KEY", raising=False)
+        assert pp.ParallelWebSearchProvider().is_available() is False
+        monkeypatch.setenv("PARALLEL_API_KEY", "k")
+        assert pp.ParallelWebSearchProvider().is_available() is True
+
+
+# ─── web_fetch (keyless extract) ─────────────────────────────────────────────
+
+class TestMcpWebFetch:
+    def _payload(self, urls):
+        return {"extract_id": "e1", "results": [
+            {"url": u, "title": f"T{i}", "publish_date": None,
+             "excerpts": [f"chunk-a-{i}", f"chunk-b-{i}"]}
+            for i, u in enumerate(urls)
+        ]}
+
+    def test_maps_to_extract_shape(self):
+        urls = ["https://a.test", "https://b.test"]
+        fake = _FakeClient(self._payload(urls))
+        with patch.object(pp.httpx, "Client", return_value=fake):
+            out = pp._mcp_web_fetch(urls, api_key=None)
+        assert [r["url"] for r in out] == urls
+        assert out[0]["content"] == "chunk-a-0\n\nchunk-b-0"
+        assert out[0]["raw_content"] == out[0]["content"]
+        assert out[0]["metadata"] == {"sourceURL": "https://a.test", "title": "T0"}
+        # tools/call targeted web_fetch, requesting full page bodies.
+        args = fake.calls[-1]["json"]["params"]
+        assert args["name"] == "web_fetch"
+        assert args["arguments"]["urls"] == urls
+        assert args["arguments"]["full_content"] is True
+        assert args["arguments"]["session_id"].startswith(f"{pp._MCP_CLIENT_NAME}-")
+
+    def test_prefers_full_content_over_excerpts(self):
+        payload = {"results": [
+            {"url": "https://a.test", "title": "T",
+             "excerpts": ["snippet"], "full_content": "the entire page body"},
+        ]}
+        fake = _FakeClient(payload)
+        with patch.object(pp.httpx, "Client", return_value=fake):
+            out = pp._mcp_web_fetch(["https://a.test"], api_key=None)
+        assert out[0]["content"] == "the entire page body"
+
+    def test_missing_url_becomes_error_entry(self):
+        # Server returns only one of the two requested URLs.
+        fake = _FakeClient(self._payload(["https://a.test"]))
+        with patch.object(pp.httpx, "Client", return_value=fake):
+            out = pp._mcp_web_fetch(["https://a.test", "https://missing.test"], api_key=None)
+        assert len(out) == 2
+        missing = [r for r in out if r["url"] == "https://missing.test"][0]
+        assert "error" in missing
+        assert missing["content"] == ""
+
+    def test_preserves_order_and_duplicate_inputs(self):
+        # MCP returns each unique URL once; output must still be one row per
+        # input, in order, including the duplicate.
+        fake = _FakeClient(self._payload(["https://a.test", "https://b.test"]))
+        urls = ["https://b.test", "https://a.test", "https://b.test"]
+        with patch.object(pp.httpx, "Client", return_value=fake):
+            out = pp._mcp_web_fetch(urls, api_key=None)
+        assert [r["url"] for r in out] == urls  # one row per input, in order
+        assert all("error" not in r for r in out)  # all three resolved
+
+    def test_extract_without_key_uses_web_fetch(self, monkeypatch):
+        monkeypatch.delenv("PARALLEL_API_KEY", raising=False)
+        captured = {}
+
+        def _fake(urls, api_key):
+            captured.update(urls=list(urls), api_key=api_key)
+            return [{"url": urls[0], "title": "", "content": "x",
+                     "raw_content": "x", "metadata": {}}]
+
+        monkeypatch.setattr(pp, "_mcp_web_fetch", _fake)
+        out = asyncio.run(pp.ParallelWebSearchProvider().extract(["https://x.test"]))
+        assert out[0]["content"] == "x"
+        assert captured == {"urls": ["https://x.test"], "api_key": None}
+
+
+# ─── keyed v1 REST search ────────────────────────────────────────────────────
+
+class TestKeyedV1Search:
+    def test_passes_max_results_and_omits_branding(self, monkeypatch):
+        monkeypatch.setenv("PARALLEL_API_KEY", "pk-live")
+        monkeypatch.delenv("PARALLEL_SEARCH_MODE", raising=False)
+        captured = {}
+
+        class _Res:
+            def __init__(self, url):
+                self.url, self.title, self.excerpts = url, "T", ["x"]
+
+        class _Resp:
+            results = [_Res(f"https://r/{i}") for i in range(10)]
+
+        class _Client:
+            def search(self, **kw):
+                captured.update(kw)
+                return _Resp()
+
+        monkeypatch.setattr(pp, "_get_sync_client", lambda: _Client())
+        out = pp.ParallelWebSearchProvider().search("q", limit=7)
+
+        assert out["success"] is True
+        # honors the caller's limit via advanced_settings.max_results
+        assert captured["advanced_settings"] == {"max_results": 7}
+        assert captured["mode"] == "advanced"            # v1 default
+        assert captured["session_id"].startswith(f"{pp._MCP_CLIENT_NAME}-")  # per-call id
+        assert len(out["data"]["web"]) == 7              # client-side slice
+        # paid path: no free-tier attribution, no [Parallel] label signal
+        assert "attribution" not in out
+        assert "provider" not in out
+
+
+# ─── v1 search mode mapping ──────────────────────────────────────────────────
+
+class TestResolveSearchMode:
+    @pytest.mark.parametrize("env,expected", [
+        (None, "advanced"),        # default
+        ("advanced", "advanced"),
+        ("basic", "basic"),
+        ("fast", "basic"),         # legacy → basic
+        ("one-shot", "basic"),     # legacy → basic
+        ("agentic", "advanced"),   # legacy → advanced
+        ("garbage", "advanced"),   # invalid → default
+        ("BASIC", "basic"),        # case-insensitive
+    ])
+    def test_mode_mapping(self, monkeypatch, env, expected):
+        if env is None:
+            monkeypatch.delenv("PARALLEL_SEARCH_MODE", raising=False)
+        else:
+            monkeypatch.setenv("PARALLEL_SEARCH_MODE", env)
+        assert pp._resolve_search_mode() == expected

tests/plugins/web/test_web_search_provider_plugins.py

@@ -193,11 +193,16 @@ class TestIsAvailable:
         assert p.is_available() is True
 
     def test_parallel_requires_api_key(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        """is_available() is key-based — it gates the registry's active-provider
+        walk/picker. (Keyless search/extract still work via the free MCP through
+        _get_backend's terminal default, independent of this flag.)
+        """
         _ensure_plugins_loaded()
         from agent.web_search_registry import get_provider
 
         p = get_provider("parallel")
         assert p is not None
+        monkeypatch.delenv("PARALLEL_API_KEY", raising=False)
         assert p.is_available() is False
         monkeypatch.setenv("PARALLEL_API_KEY", "real")
         assert p.is_available() is True
@@ -422,17 +427,33 @@ class TestErrorResponseShapes:
         assert result.get("success") is False
         assert "error" in result
 
-    def test_parallel_extract_returns_per_url_errors_when_unconfigured(self) -> None:
+    def test_parallel_extract_keyless_uses_mcp_web_fetch(
+        self, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        """Without a key, extract routes to the free MCP web_fetch tool rather
+        than erroring. The MCP transport is mocked so the test stays offline."""
         _ensure_plugins_loaded()
         from agent.web_search_registry import get_provider
+        import plugins.web.parallel.provider as parallel_provider
+
+        monkeypatch.delenv("PARALLEL_API_KEY", raising=False)
+        captured = {}
+
+        def _fake_fetch(urls, api_key):
+            captured["urls"] = list(urls)
+            captured["api_key"] = api_key
+            return [{"url": urls[0], "title": "Example", "content": "body",
+                     "raw_content": "body", "metadata": {"sourceURL": urls[0]}}]
+
+        monkeypatch.setattr(parallel_provider, "_mcp_web_fetch", _fake_fetch)
 
         p = get_provider("parallel")
         assert p is not None
         result = asyncio.run(p.extract(["https://example.com"]))
         assert isinstance(result, list)
-        assert len(result) == 1
-        assert "error" in result[0]
         assert result[0]["url"] == "https://example.com"
+        assert result[0]["content"] == "body"
+        assert captured == {"urls": ["https://example.com"], "api_key": None}
 
     def test_firecrawl_extract_returns_per_url_errors_when_unconfigured(self) -> None:
         _ensure_plugins_loaded()