Files
hermes-agent/tests/tools/test_tool_gateway_client.py
Siddharth Balyan b4d04eb8fd Connector tools (Gmail, Linear, Notion, ...) are searchable and callable through tool_search for signed-in Nous users (#106842)
* feat: add session-scoped connector access for onboarding

* fix(connectors): availability is the config flag AND the portal entitlement — no free-tier leg

The port carried a third availability leg from hermes-magic: a stored guest
(free-tier) identity short-circuits the managed-tool entitlement check. That
leg reads hermes_cli.anon_auth, which does not exist on hermes-agent main, so
connectors_available() raised ImportError inside its fail-closed try and the
whole connector surface was silently dark on a plain upstream checkout.

On this tree availability is the two-leg AND the design started with:
tools.connectors.enabled AND managed_nous_tools_enabled(). The free-tier leg
is a hermes-magic concern and belongs in hermes-magic's own delta over this
branch, next to the identity it depends on. Its integration test goes with it.

* docs(tool-search): connectors section — remote tools through the bridge

The squashed port carried the code but not the user-facing docs. Restores the
Connectors section of the Tool Search page and the connector-gateway host /
CONNECTOR_GATEWAY_URL override on the Tool Gateway page, updated for the
manage_connections tool and the pure-connector batch rule.

* fix(tool-search): connector tools rank with local tools in one pass instead of taking leftover slots

dispatch_tool_search ran BM25 over the local catalog, filled `limit` slots,
then appended connector hits only into slots left empty. On a 300-tool
catalog no slot was ever empty, so with Gmail and Google Calendar connected
"send gmail email" returned five betterstack tools and zero connector tools.

The gateway's hits for a query now become catalog entries (connector name,
slug words, description as the search text) and join the local catalog for
that query's BM25 pass. One ranking, one rarest-token admission rule for both
sources, `limit` as the total per query. The merge loop and the separate
record builder for connector hits are gone; `_shared_tool_record` serves both
sources.

The gateway search timeout rises from 8 s to 30 s. One request with six
use_cases measured 7 s, so 8 s sat on the edge and cut real answers off; the
failure path is unchanged (local-only results, no error to the model).

Live, 311 local tools + gateway, before -> after:
  "send gmail email":           5 betterstack tools -> gmail SEND_EMAIL, CREATE_EMAIL_DRAFT
  "read google calendar events": 5 betterstack tools -> googlecalendar EVENTS_LIST_ALL_CALENDARS
  "linear create issue", "betterstack incident": unchanged
Benchmark (25 labelled queries): connector recall 0.09 -> 0.82, precision@5
0.18 -> 0.59, false positives on absent intents 17 -> 2.

* refactor(tool-search): connector leg into tools/connector_search.py

tools/tool_search.py is a facade. The connector leg (gateway hits as catalog
entries for tool_search, remote schemas for tool_describe, the
connections_in_scope gate) was appended to it by the port. It now lives in
its own sibling, tools/connector_search.py, and the facade imports the three
entry points: connections_in_scope, connector_entries_by_group,
remote_schemas_for.

No behaviour change. The tool_describe remote block became
remote_schemas_for(names, current_tool_defs, connector_describe) with the
same inputs, the same silent-degradation contract and the same injection
seam the tests already use.

* fix(tool-search): at most 7 queries per call, the gateway's search limit

One tool_search call sends all its queries to the connector gateway as one
search request. The gateway answers 7 use_cases per request and returns
HTTP 502 for 8 or more (measured 2026-09-09, re-measured with one-word
use_cases: it is a count limit, not a size limit). With the client cap at
10, a model sending 8 to 10 queries lost every connector hit for that call
and saw local-only results with no error.

The shared constant splits: _MAX_QUERIES_PER_CALL = 7 for search,
_MAX_DESCRIBE_NAMES_PER_CALL = 10 for describe, which has no remote count
limit. Eight or more queries now get the existing "too many queries" retry
hint before any request is made. No chunking: one call, one request.

* fix(tool-search): the model is told that connectors__ names are manage_connections accounts

tool_search results carry names like connectors__gmail__CREATE_EMAIL_DRAFT and
manage_connections is the tool that checks and connects those accounts, but
nothing told the model the two are the same thing. A model that hit
CONNECTION_REQUIRED had to infer the fix on its own.

The tool_search description gains one sentence making the link, added at
assembly only when manage_connections is in the session's tools. Signed out
or with connectors off the tool is absent and the description is unchanged,
so it never names a tool the model cannot call. This follows the existing
rule for cross-tool references (tools/AGENTS.md): they are added dynamically
from the session's actual tool set, never hardcoded in a schema.

Tool defs are fixed for the life of a conversation, so the description is
byte-stable per conversation; this is a one-time prefix change.

Live, real get_tool_definitions() against a signed-in home: sentence present.
Same home with auth.json removed: manage_connections absent, sentence absent.

* fix(connectors): /stop halts a connector batch before the next remote call

dispatch_connector_batch runs every remote entry of a tool_call batch in
sequence. The executor only checks the interrupt flag between tools, and
the whole batch is one tool to it, so a /stop landing during entry 1 of
20 still sent the other 19 to the gateway.

The loop now reads tools.interrupt.is_interrupted before each dispatch.
Once set, it stops calling handle_function_call and fills every unstarted
slot with the loop's existing error-slot shape, code INTERRUPTED and the
message "Stopped by the user before this call was made.", so the result
envelope stays valid and the counts stay honest. Entries already
dispatched keep their real results.

Test: three connector calls where the fake client sets the interrupt on
the first execute. The client sees exactly one call and slots 2 and 3
carry INTERRUPTED. Red on the base branch, green with the fix.

* test(connections): schema assertions become dispatch contracts

test_schema_documents_wait_and_its_timeout froze description fragments
("REQUIRED", "can NOT disconnect", "Nous Portal"). A wording edit fails
it while a real regression (a disconnect that reaches the gateway) does
not. That is a snapshot of prose, not a behaviour contract.

Delete it. The requirement that wait needs connectors is already covered
by test_wait_requires_connectors. The user-only disconnect boundary is
now asserted as behaviour: action disconnect with a connector returns an
error and the fake client records no call. That replaces the earlier
de-authenticate test, which only checked that the word "dashboard"
appeared in the error text.

Test count in the file goes from 26 to 25.

* docs(tool-search): connector batches are one gateway request per entry

The user guide said a connector batch travels as one gateway request. It
does not: model_tools_connectors.dispatch_connector_batch re-enters core
dispatch per entry, and each entry becomes its own execute request in
bridge._run_remote (plus at most one literal-slug retry when the gateway
reports TOOL_NOT_FOUND under the conventional slug). The docstrings in
tools/tool_gateway/bridge.py and tools/tool_gateway/__init__.py still
described the abandoned V1 plan and claimed nothing outside the package
imports it.

Rewrite those sentences to match the code: one request per entry, in
input order, dispatched from model_tools_connectors.py, with the per-entry
approval and interrupt behaviour that motivated the split. The guide also
still showed the single-call shape tool_call(name, arguments); both
places now show the `calls: [{name, arguments}]` array the schema
advertises and note that a single local call is an array of one.

Docs only, no test.

* fix(tools): the between-turns refresh never rewrites the bridge tools

The per-turn MCP refresh folds a fresh tool snapshot into the live array
with preserve_prefix: order and membership stay, but a name present in both
takes the fresh schema. That is right for ordinary tools, whose schema is a
constant. tool_search is the one tool whose description is derived from the
session: the deferred-tool count, the embedded listing, and, on this branch,
whether manage_connections was present. A late MCP server or one failed
portal lookup (manage_connections' check_fn fails closed) changed those bytes
on the next turn, and every byte after tool_search in the cached prefix was
re-prefilled. The array also contradicted itself in that case: the flapping
manage_connections was carried forward while the description lost its hint.

The bridge entries now keep the bytes they were built with for the life of
the conversation. Nothing is lost: tool_search reads the live catalog at
dispatch, so tools that arrived late are still found; connector availability
is checked at dispatch too. The compaction-boundary rebuild (content_aware,
the one sanctioned cache break) still refreshes the description.

Consequence: connector exposure in the prompt is decided once, at agent
build, by whether the user was signed in then. That is the intended
contract.

* refactor(tool-search): normalize_tool_call_entries lives with the other argument validation

The port appended the tool_call argument parser to the tool_search facade.
The family already has tools/tool_search_validation.py for exactly this
work (schema validation of deferred call arguments), so the parser moves
there and the facade imports it. No behaviour change; the one test that
imported it now imports from the defining module.

* refactor(connectors): delete the unused batch dispatcher; _run_remote becomes run_remote

bridge.dispatch_calls and its helpers (_dispatch_calls_inner, _run_pre_dispatch,
_run_local, _error_slot, _maybe_parse_json) and the LocalDispatch / PreDispatch
seams had no production caller. Connector dispatch runs through
model_tools_connectors: dispatch_connector_batch re-enters handle_function_call
once per entry, so scope, hook, approval and middleware policy fire against each
composed name inside core dispatch, and dispatch_connector_call hands the single
planned entry to the bridge's transport function. Only tests called the batch
dispatcher, and they exercised policy seams that production never wires.

The transport function is the module's real entry point, so it drops the
underscore: _run_remote becomes run_remote, body unchanged. The module
docstring now describes the two legs that exist (availability with D32 silent
degradation, and run_remote) instead of the injected seams. Imports that only
the deleted code used are gone; merge.py is untouched because every export
still has a caller.

Tests that drove dispatch_calls are deleted where they covered the removed
seams (pre_dispatch blocks and rewrites, local_dispatch classification, mixed
batches). The literal-slug fallback, the per-entry transport failure, and the
hook rewrite reaching the gateway request body are re-targeted at
handle_function_call('tool_call', ...) with the fake client swapped in at
bridge._default_client_factory, the same seam test_connector_dispatch_policy
uses. Each re-targeted test fails when the retry is disabled in run_remote.

* fix(connectors): search keeps the twin a colliding name reaches, and says so

format_connector_name strips the toolkit prefix, so GMAIL_FETCH_PROFILE and a
literal FETCH_PROFILE on gmail both compose to connectors__gmail__FETCH_PROFILE.
describe and execute decode that name to the prefixed slug first, so the
literal twin is unreachable under it. If a vendor ever shipped both, search
could describe the literal under a name that runs the prefixed tool.

Search is the one place that sees both twins in one response. It now keeps
the twin the name reaches and drops the other with a WARNING that names both
slugs, whichever the gateway listed first. Short names stay; no marker, no
per-process map, no change to describe or execute. No such pair exists in the
live catalog today; the guard turns a silent alias into a logged one.
2026-09-10 02:21:16 +05:30

332 lines
11 KiB
Python

"""Behavior tests for ConnectorClient and the bridge entry points.
DI-callable idiom (test_managed_tool_gateway.py precedent): fakes are
injected through the constructor seams — no module mocks, no patching of
transports. FakeTransport records requests and replays queued responses.
"""
import json
from dataclasses import replace as dataclass_replace
import pytest
from tools.tool_gateway.bridge import connector_search_hits
from tools.tool_gateway.client import ConnectorClient
from tools.tool_gateway.errors import (
GatewayAuthError,
GatewayUnavailable,
IdempotencyConflict,
ToolGatewayError,
)
from tools.tool_gateway.names import vendor_slug_candidates
class FakeResponse:
def __init__(self, status_code, body):
self.status_code = status_code
self._body = body
self.text = json.dumps(body)
def json(self):
return self._body
class FakeTransport:
"""Records requests; replays queued responses (exceptions raise)."""
def __init__(self, *responses):
self.responses = list(responses)
self.requests = []
def request(self, method, url, *, headers=None, json=None, timeout=None):
self.requests.append(
{"method": method, "url": url, "headers": dict(headers or {}), "json": json}
)
outcome = self.responses.pop(0)
if isinstance(outcome, Exception):
raise outcome
return outcome
def make_client(transport):
return ConnectorClient(
transport=transport,
endpoint_resolver=lambda: "https://tool-gateway.test",
header_provider=lambda url: {"Authorization": "Bearer nous-token"},
)
def execute_envelope(results):
errors = sum(1 for r in results if r.get("error"))
return {
"results": results,
"successCount": len(results) - errors,
"errorCount": errors,
"totalCount": len(results),
}
PLAN_CALLS = [
{"name": "connectors__gmail__SEND_EMAIL", "arguments": {"to": "x"}},
{"name": "connectors__slack__POST_MESSAGE", "arguments": {}},
]
def planned(calls=PLAN_CALLS):
from tools.tool_gateway.merge import partition_calls
return tuple(
dataclass_replace(
plan,
tool=vendor_slug_candidates(plan.connector, plan.tool)[0],
)
for plan in partition_calls(calls).remote
)
# ---------------------------------------------------------------------------
# execute: request shape + idempotency
# ---------------------------------------------------------------------------
def test_execute_sends_one_request_with_camelcase_body_and_key():
transport = FakeTransport(
FakeResponse(
200,
execute_envelope(
[
{"index": 0, "connector": "gmail", "tool": "GMAIL_SEND_EMAIL", "data": {"id": "m1"}},
{"index": 1, "connector": "slack", "tool": "SLACK_POST_MESSAGE", "data": "ok"},
]
),
)
)
results = make_client(transport).execute(planned())
assert len(transport.requests) == 1
request = transport.requests[0]
assert request["url"].endswith("/v1/connectors/execute")
assert request["json"] == {
"tools": [
{"connector": "gmail", "tool": "GMAIL_SEND_EMAIL", "arguments": {"to": "x"}},
{"connector": "slack", "tool": "SLACK_POST_MESSAGE", "arguments": {}},
]
}
assert request["headers"]["x-idempotency-key"] # present, non-empty
assert request["headers"]["Authorization"] == "Bearer nous-token"
assert results == [
{"data": {"id": "m1"}, "error": None},
{"data": "ok", "error": None},
]
def test_retry_on_5xx_reuses_the_same_idempotency_key():
transport = FakeTransport(
FakeResponse(502, {"error": {"code": "BAD_GATEWAY", "message": "upstream"}}),
FakeResponse(
200,
execute_envelope(
[{"index": 0, "connector": "gmail", "tool": "GMAIL_SEND_EMAIL", "data": "sent"}]
),
),
)
results = make_client(transport).execute(planned(PLAN_CALLS[:1]))
assert len(transport.requests) == 2
first_key = transport.requests[0]["headers"]["x-idempotency-key"]
second_key = transport.requests[1]["headers"]["x-idempotency-key"]
assert first_key == second_key
assert results[0]["data"] == "sent"
def test_retry_on_transport_failure_reuses_key_then_gives_up():
transport = FakeTransport(
ConnectionError("reset"), ConnectionError("reset again")
)
with pytest.raises(ToolGatewayError) as exc_info:
make_client(transport).execute(planned(PLAN_CALLS[:1]))
assert exc_info.value.code == "TRANSPORT_ERROR"
assert len(transport.requests) == 2
assert (
transport.requests[0]["headers"]["x-idempotency-key"]
== transport.requests[1]["headers"]["x-idempotency-key"]
)
def test_4xx_never_retries():
transport = FakeTransport(
FakeResponse(400, {"error": {"code": "BAD_REQUEST", "message": "nope"}})
)
with pytest.raises(ToolGatewayError):
make_client(transport).execute(planned(PLAN_CALLS[:1]))
assert len(transport.requests) == 1
def test_409_raises_idempotency_conflict_and_never_retries():
transport = FakeTransport(
FakeResponse(
409,
{"error": {"code": "IDEMPOTENCY_CONFLICT", "message": "key reused"}},
)
)
with pytest.raises(IdempotencyConflict):
make_client(transport).execute(planned(PLAN_CALLS[:1]))
assert len(transport.requests) == 1
# ---------------------------------------------------------------------------
# status mapping + auth
# ---------------------------------------------------------------------------
def test_404_raises_gateway_unavailable_the_dark_signal():
transport = FakeTransport(FakeResponse(404, {"error": {"code": "NOT_FOUND", "message": "no route"}}))
with pytest.raises(GatewayUnavailable):
make_client(transport).execute(planned(PLAN_CALLS[:1]))
def test_401_raises_auth_error_and_missing_token_fails_fast():
transport = FakeTransport(
FakeResponse(401, {"error": {"code": "UNAUTHORIZED", "message": "expired"}})
)
with pytest.raises(GatewayAuthError):
make_client(transport).execute(planned(PLAN_CALLS[:1]))
# No token -> no request at all.
no_token = FakeTransport()
client = ConnectorClient(
transport=no_token,
endpoint_resolver=lambda: "https://tool-gateway.test",
header_provider=lambda url: {},
)
with pytest.raises(GatewayAuthError):
client.execute(planned(PLAN_CALLS[:1]))
assert no_token.requests == []
def test_connection_required_stays_inside_the_200_envelope():
transport = FakeTransport(
FakeResponse(
200,
execute_envelope(
[
{
"index": 0,
"connector": "gmail",
"tool": "GMAIL_SEND_EMAIL",
"error": {
"code": "CONNECTION_REQUIRED",
"message": "connect gmail",
"connector": "gmail",
"connectUrl": "https://example.test/connect/1",
},
}
]
),
)
)
(result,) = make_client(transport).execute(planned(PLAN_CALLS[:1]))
assert result["error"]["code"] == "CONNECTION_REQUIRED"
assert result["error"]["connect_url"] == "https://example.test/connect/1"
# ---------------------------------------------------------------------------
# bridge: connector_search_hits silent degradation (D32)
# ---------------------------------------------------------------------------
def test_search_hits_empty_on_unavailable_dark_gateway_and_exploding_client():
assert connector_search_hits(
[{"use_case": "send mail"}], availability=lambda: False
) == {}
def dark_factory():
raise GatewayUnavailable("dark", code="NOT_FOUND", status=404)
assert (
connector_search_hits(
[{"use_case": "send mail"}],
availability=lambda: True,
client_factory=dark_factory,
)
== {}
)
def boom_factory():
raise RuntimeError("boom")
assert (
connector_search_hits(
[{"use_case": "send mail"}],
availability=lambda: True,
client_factory=boom_factory,
)
== {}
)
def test_search_hits_pass_through_on_success():
class FakeClient:
def search(self, queries):
assert queries == [{"use_case": "send mail"}]
return {"results": [{"index": 1, "use_case": "send mail"}]}
hits = connector_search_hits(
[{"use_case": "send mail"}],
availability=lambda: True,
client_factory=lambda: FakeClient(),
)
assert hits["results"][0]["use_case"] == "send mail"
# ---------------------------------------------------------------------------
# default endpoint resolver: the SHARED origin, not a fabricated vendor
# ---------------------------------------------------------------------------
_GATEWAY_ENV_KEYS = (
"TOOL_GATEWAY_URL",
"CONNECTOR_GATEWAY_URL",
"TOOL_GATEWAY_DOMAIN",
"TOOL_GATEWAY_SCHEME",
)
def _resolve_with_env(**overrides):
"""Run the default resolver with ONLY the given gateway env keys set."""
import os
from unittest.mock import patch
from tools.tool_gateway.client import _default_endpoint_resolver
env = {k: v for k, v in os.environ.items() if k not in _GATEWAY_ENV_KEYS}
env.update(overrides)
with patch.dict("os.environ", env, clear=True):
return _default_endpoint_resolver()
def test_default_resolver_uses_the_connector_gateway_origin():
# Connector routes live on the connectors deployment's own host, so the
# resolver wants that origin — never a fabricated "connectors" vendor
# passthrough host, and never the media/on-origin-vendor host.
assert _resolve_with_env(CONNECTOR_GATEWAY_URL="http://127.0.0.1:3009") == (
"http://127.0.0.1:3009"
)
assert _resolve_with_env(TOOL_GATEWAY_DOMAIN="gw.example.com") == (
"https://connector-gateway.gw.example.com"
)
def test_default_resolver_ignores_the_media_host_override():
# TOOL_GATEWAY_URL moves the media/on-origin-vendor host only. Letting it
# drag the connectors client along would silently point connector calls at
# a host that does not serve them.
assert _resolve_with_env(
TOOL_GATEWAY_URL="http://127.0.0.1:3009",
TOOL_GATEWAY_DOMAIN="gw.example.com",
) == "https://connector-gateway.gw.example.com"
def test_default_resolver_is_none_on_a_misconfigured_scheme():
assert _resolve_with_env(TOOL_GATEWAY_SCHEME="ftp") is None