docs(proxy): round-2 — address Codex round-1 on #202

Codex round-1 flagged two blockers:

1. cache-telemetry comment was factually wrong. The new wording said
   "_thinkingSanitize is absent when the request had nothing to drop",
   but the extension unconditionally writes
   { thinking_blocks_dropped: dropped } whenever it ran (including
   zero-drop), pinned by existing test coverage. Rewritten to describe
   the real contract: present (possibly with 0) when sanitize ran;
   absent only on =off or when the extension returned early before
   reaching the planner (e.g., body.messages not an array).

2. Sweep was incomplete. Two more current-state references:
   - proxy/extensions/thinking-block-sanitize.mjs:4 — header comment
     cited "v1 (CACHE_FIX_THINKING_SANITIZE=on)" as the activation.
     Updated to "v1 (default since v4.0.0; CACHE_FIX_THINKING_SANITIZE
     unset or =on)".
   - test/proxy-thinking-block-sanitize.test.mjs:194 — test title
     started with "onRequest: opt-in on with nothing to drop". Renamed
     to "onRequest: =on with nothing to drop".

Codex also flagged 4 lines in README.zh.md. Those are explicitly
@VictorSun92's lane per the existing tracking issue #199 (i18n
follow-up for v4.0.0 behavior changes; tagged @VictorSun92 for zh,
@ArkNill for ko). Not in scope for this PR.

1004/1004 tests pass.

Refs #199, #201, #202.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: vsits-team-lead-agent[bot]

proxy/extensions/cache-telemetry.mjs

@@ -239,8 +239,10 @@ export default {
           // that extension is disabled or produced nothing this request.
           ...(ctx.meta._sessionHealth || {}),
           // Additive thinking-block-sanitize drop count (order 550). On by
-          // default since v4.0.0; absent when CACHE_FIX_THINKING_SANITIZE=off
-          // (explicit disable) or when the request had nothing to drop.
+          // default since v4.0.0; present (possibly with thinking_blocks_dropped:0)
+          // whenever sanitize ran. Absent when CACHE_FIX_THINKING_SANITIZE=off
+          // or when the extension returned early before reaching the planner
+          // (e.g., body.messages not an array).
           ...(ctx.meta._thinkingSanitize || {}),
           // Additive thinking-block-sanitize v2 fields (order 550, opt-in via
           // CACHE_FIX_THINKING_SANITIZE=v2). Optional — absent unless v2 is

proxy/extensions/thinking-block-sanitize.mjs

@@ -1,7 +1,7 @@
 // thinking-block-sanitize — request-path mitigation for the CC thinking-desync
 // wedge (anthropics/claude-code#63147).
 //
-// v1 (CACHE_FIX_THINKING_SANITIZE=on): On replay paths (resume / --continue /
+// v1 (default since v4.0.0; CACHE_FIX_THINKING_SANITIZE unset or =on): On replay paths (resume / --continue /
 // auto-compaction / parallel-tool-cancel), CC re-sends prior assistant turns'
 // thinking in the OMITTED shape `{ type:"thinking", thinking:"", signature }`.
 // The API rejects modified thinking in the *latest* assistant message with a

test/proxy-thinking-block-sanitize.test.mjs

@@ -191,7 +191,7 @@ test("onRequest: explicit =on matches the default (back-compat)", async () => {
   });
 });
 
-test("onRequest: opt-in on with nothing to drop emits a zero count and leaves the body intact", async () => {
+test("onRequest: =on with nothing to drop emits a zero count and leaves the body intact", async () => {
   await withSanitize("on", async () => {
     const ctx = {
       body: { messages: [{ role: "assistant", content: [realThinking(), text("a")] }] },