mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-24 05:41:40 +00:00
feat(gateway): wire clarify tool with inline keyboard buttons on Telegram (#24199)
The clarify tool returned 'not available in this execution context' for every gateway-mode agent because gateway/run.py never passed clarify_callback into the AIAgent constructor. Schema actively encouraged calling it; users never saw the question. Changes: - tools/clarify_gateway.py — new event-based primitive mirroring tools/approval.py: register/wait_for_response/resolve_gateway_clarify with per-session FIFO, threading.Event blocking with 1s heartbeat slices (so the inactivity watchdog keeps ticking), and clear_session for boundary cleanup. - gateway/platforms/base.py — abstract send_clarify with a numbered-text fallback so every adapter (Discord, Slack, WhatsApp, Signal, Matrix, etc.) gets a working clarify out of the box. Plus an active-session bypass: when the agent is blocked on a text-awaiting clarify, the next non-command message routes inline to the runner's intercept instead of being queued + triggering an interrupt. Same shape as the /approve deadlock fix from PR #4926. - gateway/platforms/telegram.py — concrete send_clarify renders one inline button per choice plus '✏️ Other (type answer)'. cl: callback handler resolves numeric choices immediately, flips to text-capture mode for Other, with the same authorization guards as exec/slash approvals. - gateway/run.py — clarify_callback wired at the cached-agent per-turn callback assignment site (only the user-facing agent path; cron and hygiene-compress agents have no human attached). Bridges sync→async via run_coroutine_threadsafe, blocks with the configured timeout, and returns a '[user did not respond within Xm]' sentinel on timeout so the agent adapts rather than pinning the running-agent guard. Text- intercept added to _handle_message before slash-confirm intercept (skipping slash commands). clear_session called in the run's finally to cancel any orphan entries. - hermes_cli/config.py — agent.clarify_timeout default 600s. - website/docs/user-guide/messaging/telegram.md — Interactive Prompts section. Tests: - tests/tools/test_clarify_gateway.py (14 tests) — full primitive coverage: button resolve, open-ended auto-await, Other flip, timeout None, unknown-id idempotency, clear_session cancellation, FIFO ordering, register/unregister notify, config default. - tests/gateway/test_telegram_clarify_buttons.py (12 tests) — render paths (multi-choice/open-ended/long-label/HTML-escape/not-connected), callback dispatch (numeric resolve/Other flip/already-resolved/ unauthorized/invalid-token), and base-adapter text fallback. Out of scope: bot-to-bot, guest mode, checklists, poll media, live photos. Closes #24191.
This commit is contained in:
parent
76bbb94be4
commit
29d7c244c5
8 changed files with 1347 additions and 0 deletions
|
|
@ -1743,6 +1743,55 @@ class BasePlatformAdapter(ABC):
|
|||
"""
|
||||
return SendResult(success=False, error="Not supported")
|
||||
|
||||
async def send_clarify(
|
||||
self,
|
||||
chat_id: str,
|
||||
question: str,
|
||||
choices: Optional[list],
|
||||
clarify_id: str,
|
||||
session_key: str,
|
||||
metadata: Optional[Dict[str, Any]] = None,
|
||||
) -> SendResult:
|
||||
"""Send a clarify prompt to the user.
|
||||
|
||||
Two render modes:
|
||||
|
||||
* **Multiple choice** (``choices`` is a non-empty list) — adapters
|
||||
that override this should render inline buttons (one per choice
|
||||
plus a final "Other" / free-text option). Button callbacks
|
||||
MUST resolve via
|
||||
``tools.clarify_gateway.resolve_gateway_clarify(clarify_id, response)``
|
||||
with the chosen string. Picking the "Other" button calls
|
||||
``mark_awaiting_text(clarify_id)`` so the next message in the
|
||||
session is captured as the response.
|
||||
|
||||
* **Open-ended** (``choices`` is None or empty) — render the
|
||||
question as a plain text message; the next user message in the
|
||||
session is captured by the gateway's text-intercept and
|
||||
resolves the clarify automatically (see
|
||||
``GatewayRunner._maybe_intercept_clarify_text``).
|
||||
|
||||
The default implementation falls back to a numbered text list,
|
||||
which works on every platform — the user replies with a number
|
||||
("2") or with the literal choice text, and the gateway intercepts
|
||||
and resolves. Adapters with native button UIs (Telegram, Discord)
|
||||
SHOULD override this for a richer UX.
|
||||
"""
|
||||
if choices:
|
||||
lines = [f"❓ {question}", ""]
|
||||
for i, choice in enumerate(choices, start=1):
|
||||
lines.append(f" {i}. {choice}")
|
||||
lines.append("")
|
||||
lines.append("Reply with the number, the option text, or your own answer.")
|
||||
text = "\n".join(lines)
|
||||
else:
|
||||
text = f"❓ {question}"
|
||||
return await self.send(
|
||||
chat_id=chat_id,
|
||||
content=text,
|
||||
metadata=metadata,
|
||||
)
|
||||
|
||||
async def send_private_notice(
|
||||
self,
|
||||
chat_id: str,
|
||||
|
|
@ -2831,6 +2880,58 @@ class BasePlatformAdapter(ABC):
|
|||
logger.error("[%s] Command '/%s' dispatch failed: %s", self.name, cmd, e, exc_info=True)
|
||||
return
|
||||
|
||||
# Clarify text-capture bypass: if the agent is blocked on a
|
||||
# clarify_tool call awaiting a free-form text response (open-
|
||||
# ended clarify, or user picked "Other"), the next non-command
|
||||
# message in this session MUST reach the runner so the
|
||||
# clarify-intercept can resolve it and unblock the agent.
|
||||
#
|
||||
# Without this bypass: the message gets queued in
|
||||
# _pending_messages AND triggers an interrupt, killing the
|
||||
# agent run mid-clarify and discarding the user's answer.
|
||||
# Same shape as the /approve deadlock fix (PR #4926) — both
|
||||
# cases are "agent thread blocked on Event.wait, message must
|
||||
# reach the resolver before being treated as a new turn."
|
||||
if not cmd:
|
||||
try:
|
||||
from tools import clarify_gateway as _clarify_mod
|
||||
_has_text_clarify = (
|
||||
_clarify_mod.get_pending_for_session(session_key) is not None
|
||||
)
|
||||
except Exception:
|
||||
_has_text_clarify = False
|
||||
|
||||
if _has_text_clarify:
|
||||
logger.debug(
|
||||
"[%s] Routing message to clarify text-intercept for %s",
|
||||
self.name, session_key,
|
||||
)
|
||||
try:
|
||||
_thread_meta = _thread_metadata_for_source(
|
||||
event.source, _reply_anchor_for_event(event)
|
||||
)
|
||||
response = await self._message_handler(event)
|
||||
_text, _eph_ttl = self._unwrap_ephemeral(response)
|
||||
if _text:
|
||||
_r = await self._send_with_retry(
|
||||
chat_id=event.source.chat_id,
|
||||
content=_text,
|
||||
reply_to=_reply_anchor_for_event(event),
|
||||
metadata=_thread_meta,
|
||||
)
|
||||
if _eph_ttl > 0 and _r.success and _r.message_id:
|
||||
self._schedule_ephemeral_delete(
|
||||
chat_id=event.source.chat_id,
|
||||
message_id=_r.message_id,
|
||||
ttl_seconds=_eph_ttl,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
"[%s] Clarify text-intercept dispatch failed: %s",
|
||||
self.name, e, exc_info=True,
|
||||
)
|
||||
return
|
||||
|
||||
if self._busy_session_handler is not None:
|
||||
try:
|
||||
if await self._busy_session_handler(event, session_key):
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue