gate: streaming — the model's events relayed as they come, the fringe as the last block

Bamidbar 15:39 u'reitem oto — the fringe must be seen, so a streaming
client gets it too. With "stream": true the request is opened
asynchronously (Gate.Upstream.open_stream/4, httpc stream: :self) and
Gate.Stream relays every complete SSE event to the caller unchanged
while gathering the text deltas; the terminal events (Anthropic
message_delta + message_stop; OpenAI the finish_reason chunk + [DONE])
are held until the gathered text has been examined, then released
behind the fringe sent as one more text block, with the `bikoret` object
added to the terminal event the client already parses. No X-Bikoret-*
headers on a stream (they leave before the model speaks); no rebuke on a
stream (nothing streamed can be taken back — 422). An examination that
fails after the stream began is said in the trailer ("— bikoret: not
examined (…)"), never silent. One api_calls_external gathered before the
call, as for any pass. Tamid §1.1, Construction §3.10, KOHEN. Doorpost
40e7d7d1…. Elixir 612/0 (read before this commit).

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

KOHEN.md

@@ -590,6 +590,9 @@ curl -s -X POST http://<host>/gate/anthropic/v1/messages \
 
 `X-Bikoret-Rebuke: once` — a lo_tov reply is answered once more with
 the finding, and the second reply is delivered marked with both refs.
+Streaming clients (`"stream": true`, Claude Code among them) are carried
+through as they stream; the fringe arrives as the last text block and the
+`bikoret` object on the final event — no headers, no rebuke on a stream.
 Each upstream call spends one `api_calls_external` of the day's manna
 (Day 4): a provision with 0 shuts the gate (503 MANNA_DEPLETED) while
 the bedikah by hand still runs. Streaming is refused (422). A non-200