mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-28 18:19:28 +00:00
One relay adapter fronts N platforms on one WS, but the capability surface (MAX_MESSAGE_LENGTH / message_len_fn) was a scalar from whichever descriptor resolved the handshake — and the transport's read loop OVERWROTE it on every descriptor frame (last-writer-wins). A Discord chat on a gateway whose applied descriptor was Telegram's inherited the 4,096-char cap and over-sent into Discord's 2,000-char API 400 (observed live: 2,543/2,641-char replies silently lost while inbound kept working). - ws_transport: accumulate one descriptor per platform in _descriptors_by_platform (exposed via descriptor_for_platform); the FIRST descriptor of a connection generation stays the session default instead of last-writer-wins; the map resets on re-dial. - BasePlatformAdapter: new max_message_length_for_chat / message_len_fn_for_chat hooks defaulting to the scalar surface (native single-platform adapters unchanged). - RelayAdapter: overrides resolve the chat's platform from _platform_by_chat (the same map per-frame egress uses) and look up that platform's negotiated descriptor; falls back to the scalar for unknown chats/transports. - stream_consumer (streaming budget, _raw_message_limit, fallback-continuation chunking) + run.py tool-progress limit now resolve per-chat. Tests: tests/gateway/relay/test_relay_per_platform_caps.py (7) — verified fail-without/pass-with (all 7 fail with the fix stashed). Relay + stream consumer suites green (213 + 223). |
||
|---|---|---|
| .. | ||
| qqbot | ||
| __init__.py | ||
| _http_client_limits.py | ||
| ADDING_A_PLATFORM.md | ||
| api_server.py | ||
| base.py | ||
| bluebubbles.py | ||
| helpers.py | ||
| msgraph_webhook.py | ||
| signal.py | ||
| signal_format.py | ||
| signal_rate_limit.py | ||
| webhook.py | ||
| webhook_filters.py | ||
| weixin.py | ||
| whatsapp_cloud.py | ||
| whatsapp_common.py | ||
| yuanbao.py | ||
| yuanbao_media.py | ||
| yuanbao_proto.py | ||
| yuanbao_sticker.py | ||