* feat(browser): store full snapshots on truncation; make eval denylist opt-in
Two harness fixes motivated by BU_Bench results where fixed-verb + lossy
observation cost Hermes heavily vs code-driven browser agents:
1. Snapshot truncation no longer loses content. When a snapshot exceeds
the 8000-char threshold, the complete accessibility tree is saved to
cache/web (same truncate-and-store pattern as web_extract) and the
truncated view / LLM summary includes the file path plus a ready-made
read_file call. Element refs beyond the cut are recoverable without
re-snapshotting. Stored copies are force-redacted and capped at 2MB;
content-hash filenames dedupe repeated snapshots of the same page.
2. The browser_console(expression=...) sensitive-primitive denylist is
now opt-in via browser.restrict_evaluate (default false). The
names-based denylist blocked legitimate DOM extraction — any selector
or expression containing 'fetch', 'cookie', 'input', etc. — which
crippled the agent's only programmatic page-inspection path. The
SSRF/private-URL egress guards in _browser_eval are independent of
this policy and remain always-on. browser.allow_unsafe_evaluate keeps
its meaning (bypass the denylist) for configs that already set it.
* test: update None-guard test for stored-snapshot pointer in _extract_relevant_content
test_normal_content_returned pinned the exact return value; the summary
now carries a pointer to the stored full snapshot. Assert the summary
passes through and the pointer is present instead.
* feat(browser): align snapshot threshold with web_extract's 15k char budget
SNAPSHOT_SUMMARIZE_THRESHOLD 8000 -> 15000, matching
web_tools.DEFAULT_EXTRACT_CHAR_LIMIT so the snapshot and web_extract
truncate-and-store paths give the model the same per-page budget.
_truncate_snapshot's default max_chars now follows the constant.
Invariant test added; docs (en+zh) and CLI tip updated.
Translates the full English docs corpus (335 files) into Simplified
Chinese under website/i18n/zh-Hans/. Combined with PR #31895 (cross-
locale link fix), the 简体中文 locale toggle now serves a complete
Chinese site with working cross-page navigation.
Pipeline:
- Claude Sonnet 4.6 via OpenRouter, 8-way concurrent
- Preserves frontmatter keys, code blocks, MDX/JSX, link URLs, brand
names, and technical jargon (prompt/token/hook/MCP/ACP/etc.)
- Translates only frontmatter title/description and prose
- Two largest files (configuration.md 93KB, research-paper-writing.md
107KB) retried with 64K max_tokens after initial fence-drift
- 3 manual post-fixes for MDX edge cases the model didn't escape:
< in optional-skills-catalog table, double-quotes in an alt= tag,
and a bare URL adjacent to a full-width period
Cost: ~$30 total (Sonnet 4.6 input $3/M + output $15/M).
Verified `npm run build` succeeds for both en and zh-Hans locales,
no double-prefixed /docs/zh-Hans/docs/ URLs in rendered output,
all in-page navigation resolves correctly.
Translations are machine-generated and may need human review on
specific pages — but they're an enormous improvement over the
previous state (3 zh-Hans pages out of 335).
Teknium