fix: voice answers no longer wait behind chat answers; late chat answers are dropped

- The voice worker writes voice and chat replies in separate lanes (one
  of each at a time), so a chat answer being written never holds up a
  voice answer. Tests: a voice reply finishes while a chat reply is still
  running; replies of one kind stay one at a time.
- A chat answer arriving 5 minutes or more after it was asked is not
  posted, checked when it arrives.
- Specs: the lanes, and that Strata needs --parallel 2 for both lanes'
  LLM calls to run at once until the app starts Strata itself (M5).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
javis-bot
2026-11-11 22:42:30 +09:00
parent a70ccda37e
commit 2f69557e1b
5 changed files with 85 additions and 10 deletions

View File

@@ -52,7 +52,9 @@ class VoiceWorker:
self.tick_s = tick_s
self.history = history # jarvis.memory.history.HistoryStore or None
self.brain = brain
self.brain_lock = asyncio.Lock() # one reply at a time
# One reply at a time per lane: voice answers never wait behind a chat answer (conversation.md:
# with an "answer everything" chat channel the LLM takes two or more requests at once).
self.brain_lanes = {"voice": asyncio.Lock(), "chat": asyncio.Lock()}
self.chat_timeout_s = chat_timeout_s
# chat_action ids are unique across connections and worker runs, so a late answer from an
# earlier connection (or an earlier worker) never completes a newer action.
@@ -545,7 +547,7 @@ class Session:
async def _reply_inner(self, rid: str, user: str, text: str, via: str, speak: bool) -> None:
w = self.worker
channel = self.voice_channel
async with w.brain_lock:
async with w.brain_lanes[via]:
if self.closed:
return
now = time.time()

View File

@@ -218,7 +218,9 @@ which carry Discord's own time.
or when it was said, or who heard it. A final said outside a voice channel is not stored.
- Chat messages are stored only as given; the app sends only registered channels.
- `reply` asks the brain to answer `user`'s `text`. The worker builds the history context for that
user (their scope only) and runs the reply engine on a worker thread, one reply at a time.
user (their scope only) and runs the reply engine on a worker thread, one voice reply and one chat
reply at a time: the two kinds have separate lanes, so a voice answer never waits behind a chat
answer (`app/src/conversation.spec.md`, chat calls).
`reply_text` carries the answer (`failed: true` with empty text when the brain gave none). A voice
answer (`via: "voice"`) is stored as a `reply` record to the user in the current channel; a chat
answer is stored when the app reports the sent message as `chat_message` with `to`. With