gate: Claude Code behind it — OAuth bearer, anthropic-beta, token counting, the gate's own watch

A coding agent's traffic differs from a hand-made request: with a
subscription Claude Code authenticates with an OAuth bearer and sends
anthropic-beta; it counts tokens at /v1/messages/count_tokens; it makes a
request per tool call; its tool-only turns have no text; its context runs
to megabytes. So: with the courtyard key in X-Bikoret-Key, the caller's
Authorization: Bearer is forwarded to Anthropic as its credential, and
anthropic-beta with it; count_tokens is carried through unexamined and
uncharged; the watch counts the gate at its own windows (120/min,
2,000/h per key — tier :gate); a reply with no text is delivered as it
came with bikoret.verdict "none" and no fringe block (stream and
non-stream); the sources keep the newest user turns whole and drop the
oldest past 1 MiB. Ingress body 32 MiB; ConfigMap manna amounts raised
to 5000/5000 (the kohen's lever). Tamid §1.1, KOHEN "Claude Code behind
the gate". Doorpost re-pinned. Elixir 617/0 read before this commit;
gate_test 25.

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

specs/bikoret_tamid.md

@@ -443,9 +443,14 @@ POST /gate/openai/v1/chat/completions   body: the OpenAI Chat Completions reques
 Headers:
   Authorization: Bearer <courtyard key>        (or X-Bikoret-Key: <courtyard key>)
   x-api-key: <your Anthropic key>              forwarded; never stored, never logged
+  Authorization: Bearer <your Anthropic OAuth token>   with the courtyard key in X-Bikoret-Key
+                                               (what Claude Code sends with a subscription)
   Authorization: Bearer <your OpenAI key>      with the courtyard key in X-Bikoret-Key
-  anthropic-version: 2023-06-01                forwarded (default when absent)
-  X-Bikoret-Rebuke: once                     optional — hocheach tochiach
+  anthropic-version, anthropic-beta            forwarded as sent (version defaults to 2023-06-01)
+  X-Bikoret-Rebuke: once                       optional — hocheach tochiach
+
+POST /gate/anthropic/v1/messages/count_tokens  carried through under the caller's
+                                               credential; not a reply: not examined, no manna
 
 Response (200): the upstream's reply, with
   - the fringe appended to its last text block:
@@ -482,11 +487,16 @@ reply is examined like the first (its record carries rebukes: <first
 ref>) and is the one delivered, marked with both. Never a third.
 
 Manna: one api_calls_external per upstream call, one compute unit per
-examination; spent → 503 MANNA_DEPLETED before any call. Errors: 401/403
-(courtyard key), 422 (no upstream key, no messages, stream), 502
-UPSTREAM_UNAVAILABLE (the gate made no verdict and delivered nothing),
-503 KORBAN/TALMUDIC_UNAVAILABLE (a 200 from the model is never delivered
-unexamined).
+examination; spent → 503 MANNA_DEPLETED before any call. The watch counts
+the gate at its own windows — 120 a minute, 2,000 an hour per key — a
+coding agent behind it makes a request per tool call. A reply with no
+text (tool use only) is not a reply to a reader: delivered as it came,
+no fringe, `bikoret.verdict: "none", reason: "no text"`. The sources
+keep the newest user turns whole and drop the oldest past 1 MiB. Errors:
+401/403 (courtyard key), 422 (no upstream credential, no messages,
+stream with rebuke), 502 UPSTREAM_UNAVAILABLE (the gate made no verdict
+and delivered nothing), 503 KORBAN/TALMUDIC_UNAVAILABLE (a 200 from the
+model is never delivered unexamined).
 ```
 
 **Anchoring is deterministic and lexical** (`korban_processor/bedikah.py`):