opentui(phase3): launcher integration — HERMES_TUI_ENGINE dual-engine
hermes --tui launches the native OpenTUI engine (Bun) when HERMES_TUI_ENGINE=opentui (env) or display.tui_engine=opentui (config); Ink stays the default and the shipping path is untouched. - _resolve_tui_engine() (env > config > ink); refuses opentui on Windows/Termux (no Bun) -> falls back to ink with a notice. - _make_opentui_argv() -> [bun, src/entry.real.tsx] (no build step). - _bun_bin() with HERMES_BUN override. - Branch at top of _make_tui_argv BEFORE _ensure_tui_node (Bun-only host must not bootstrap Node). - Gate _launch_tui NODE_OPTIONS/--max-old-space-size on engine==ink (Bun is JSC; the V8 flag errors/ignores). Verified end-to-end via tmux: real hermes --tui -> Bun -> OpenTUI -> real Python gateway streamed a real reply. No-flag default still ink.
This commit is contained in:
alt-glitch
@@ -147,15 +147,8 @@ class GatewayStreamConsumer:
|
||||
self._edit_supported = True # Disabled when progressive edits are no longer usable
|
||||
self._last_edit_time = 0.0
|
||||
self._last_sent_text = "" # Track last-sent text to skip redundant edits
|
||||
# True when the most recent _send_or_edit split-and-delivered across
|
||||
# continuation messages (the adapter adopted a new message id).
|
||||
self._last_edit_overflowed = False
|
||||
self._fallback_final_send = False
|
||||
self._fallback_prefix = ""
|
||||
# True when fallback is sending only the missing tail after a partial
|
||||
# Telegram overflow delivery. In that case the already-visible prefix
|
||||
# is intentional content, not a stale preview to delete.
|
||||
self._fallback_preserve_partial_messages = False
|
||||
self._flood_strikes = 0 # Consecutive flood-control edit failures
|
||||
self._current_edit_interval = self.cfg.edit_interval # Adaptive backoff
|
||||
self._final_response_sent = False
|
||||
@@ -268,7 +261,6 @@ class GatewayStreamConsumer:
|
||||
self._last_sent_text = ""
|
||||
self._fallback_final_send = False
|
||||
self._fallback_prefix = ""
|
||||
self._fallback_preserve_partial_messages = False
|
||||
# #29346: a tool/segment boundary means what we delivered was an interim
|
||||
# preamble, not the final answer — clear the flags so a premature setter
|
||||
# can't fool the gateway. Safe: got_done returns before any reset, and
|
||||
@@ -589,20 +581,14 @@ class GatewayStreamConsumer:
|
||||
if self._accumulated:
|
||||
if self._fallback_final_send:
|
||||
await self._send_fallback_final(self._accumulated)
|
||||
elif current_update_visible and (
|
||||
not self._adapter_requires_finalize
|
||||
or self._last_edit_overflowed
|
||||
elif (
|
||||
current_update_visible
|
||||
and not self._adapter_requires_finalize
|
||||
):
|
||||
# Mid-stream edit above already delivered the
|
||||
# final accumulated content. Skip the redundant
|
||||
# final edit for adapters that don't need an
|
||||
# explicit finalize signal, and for any adapter
|
||||
# when that edit split-and-delivered across
|
||||
# continuations: the split edit carried
|
||||
# finalize=True itself, and re-finalizing with
|
||||
# the full text would overflow-split again into
|
||||
# the adopted continuation, duplicating chunks
|
||||
# on screen.
|
||||
# final edit — but only for adapters that don't
|
||||
# need an explicit finalize signal.
|
||||
self._final_response_sent = True
|
||||
self._final_content_delivered = True
|
||||
elif self._message_id:
|
||||
@@ -661,21 +647,11 @@ class GatewayStreamConsumer:
|
||||
await asyncio.sleep(0.05) # Small yield to not busy-loop
|
||||
|
||||
except asyncio.CancelledError:
|
||||
# Best-effort final edit on cancellation. finalize=True so
|
||||
# REQUIRES_EDIT_FINALIZE platforms (Telegram) apply final
|
||||
# formatting — a plain edit here would leave the entire reply
|
||||
# rendered as a raw streaming preview while the success flags
|
||||
# below suppress the gateway's formatted re-send.
|
||||
# is_turn_final=False keeps _try_fresh_final from setting
|
||||
# _final_response_sent itself; this handler owns the flags.
|
||||
# Best-effort final edit on cancellation
|
||||
_best_effort_ok = False
|
||||
if self._accumulated and self._message_id:
|
||||
try:
|
||||
_best_effort_ok = bool(
|
||||
await self._send_or_edit(
|
||||
self._accumulated, finalize=True, is_turn_final=False,
|
||||
)
|
||||
)
|
||||
_best_effort_ok = bool(await self._send_or_edit(self._accumulated))
|
||||
except Exception:
|
||||
pass
|
||||
# Only confirm final delivery if the best-effort send above
|
||||
@@ -891,21 +867,11 @@ class GatewayStreamConsumer:
|
||||
self._notify_new_message()
|
||||
|
||||
# Remove the frozen partial message so the user only sees the
|
||||
# complete fallback response. ONLY safe when the fallback re-sent
|
||||
# the FULL final text (continuation == final_text). When the
|
||||
# prefix-based dedup above sent only the missing TAIL, the partial
|
||||
# message IS the head of the answer — deleting it leaves the user
|
||||
# with only the last part of the response (the "Gemini sent only
|
||||
# the second half" symptom). Best-effort — if the platform doesn't
|
||||
# complete fallback response. Best-effort — if the platform doesn't
|
||||
# implement ``delete_message``, the delete fails (flood control still
|
||||
# active, bot lacks permission, message too old to delete), the
|
||||
# partial remains but at least the full answer was delivered.
|
||||
if (
|
||||
stale_message_id
|
||||
and stale_message_id != last_message_id
|
||||
and not self._fallback_preserve_partial_messages
|
||||
and continuation == final_text
|
||||
):
|
||||
if stale_message_id and stale_message_id != last_message_id:
|
||||
delete_fn = getattr(self.adapter, "delete_message", None)
|
||||
if delete_fn is not None:
|
||||
try:
|
||||
@@ -922,7 +888,6 @@ class GatewayStreamConsumer:
|
||||
self._final_content_delivered = True
|
||||
self._last_sent_text = chunks[-1]
|
||||
self._fallback_prefix = ""
|
||||
self._fallback_preserve_partial_messages = False
|
||||
|
||||
def _is_flood_error(self, result) -> bool:
|
||||
"""Check if a SendResult failure is due to flood control / rate limiting."""
|
||||
@@ -1243,7 +1208,6 @@ class GatewayStreamConsumer:
|
||||
return True
|
||||
# Failure already disabled drafts for this run; fall through to
|
||||
# the regular edit/send path below.
|
||||
self._last_edit_overflowed = False
|
||||
try:
|
||||
if self._message_id is not None:
|
||||
if self._edit_supported:
|
||||
@@ -1300,7 +1264,6 @@ class GatewayStreamConsumer:
|
||||
and result.message_id
|
||||
and result.message_id != self._message_id
|
||||
):
|
||||
self._last_edit_overflowed = True
|
||||
self._message_id = str(result.message_id)
|
||||
self._message_created_ts = time.monotonic()
|
||||
self._last_sent_text = ""
|
||||
@@ -1311,35 +1274,6 @@ class GatewayStreamConsumer:
|
||||
self._flood_strikes = 0
|
||||
return True
|
||||
else:
|
||||
raw_response = getattr(result, "raw_response", None)
|
||||
if isinstance(raw_response, dict) and raw_response.get("partial_overflow"):
|
||||
# Telegram edited/sent one or more overflow chunks,
|
||||
# but not the complete response. Preserve the
|
||||
# visible prefix so the got_done fallback sends the
|
||||
# missing tail instead of marking a clipped topic
|
||||
# reply as final delivery.
|
||||
self._message_id = str(
|
||||
raw_response.get("last_message_id")
|
||||
or result.message_id
|
||||
or self._message_id
|
||||
)
|
||||
delivered_prefix = raw_response.get("delivered_prefix")
|
||||
if isinstance(delivered_prefix, str) and delivered_prefix:
|
||||
self._last_sent_text = delivered_prefix
|
||||
self._fallback_prefix = delivered_prefix
|
||||
self._fallback_preserve_partial_messages = text.startswith(
|
||||
delivered_prefix
|
||||
)
|
||||
else:
|
||||
self._fallback_prefix = self._visible_prefix()
|
||||
self._fallback_preserve_partial_messages = False
|
||||
self._fallback_final_send = True
|
||||
self._edit_supported = False
|
||||
self._already_sent = True
|
||||
if getattr(result, "continuation_message_ids", ()):
|
||||
self._notify_new_message()
|
||||
return False
|
||||
|
||||
# Edit failed. If this looks like flood control / rate
|
||||
# limiting, use adaptive backoff: double the edit interval
|
||||
# and retry on the next cycle. Only permanently disable
|
||||
|
||||
Reference in New Issue
Block a user