v3.3.0: fix auto-continue class breakage, add MAX_TOKENS auto-continue for Gemini/Antigravity, bump version label

This commit is contained in:
Roman
2026-05-20 22:00:49 +04:00
Unverified
parent e2f20810f0
commit f184fdf9b9
4 changed files with 88 additions and 16 deletions

View File

@@ -31,23 +31,9 @@ CHANGELOG = [
"Added Gemini CLI OAuth backend using public Gemini CLI OAuth client",
"Antigravity now creates files via tool calls — full Codex agent loop with Gemini-style history hardening",
"Fixed tool-call streaming: function_call_arguments delta/done events, thought signatures, functionResponse name matching",
"Auto-continue on MAX_TOKENS — proxy transparently requests continuation for truncated Gemini/Antigravity responses",
"Added Endpoint Doctor, adaptive BGP scoring, provider policies, adaptive compaction, log redaction",
]),
("3.1.0", "2026-05-20", [
"Initial Antigravity/Gemini CLI OAuth split, history hardening, SSE fixes",
]),
("3.0.0", "2026-05-20", [
"ThreadingHTTPServer with dynamic proxy ports and health-gated Codex launch",
"Atomic config writes, safe cleanup registry, graceful shutdown, and buffered SSE streaming",
"Usage Dashboard v2, TCP_NODELAY streaming, Anthropic prompt caching, and batched usage stats",
]),
("2.6.1", "2026-05-20", [
"Google OAuth rebuilt to emulate Gemini CLI — no client_secret.json needed",
"Uses Google's public OAuth client_id (same as gemini-cli)",
"PKCE + CSRF state protection for secure auth",
"Just click OAuth Login → browser opens → authorize → done",
"Includes cloud-platform scope for Gemini Code Assist compatibility",
]),
("2.6.0", "2026-05-20", [
"Usage Dashboard — per-provider request/token/latency tracking",
"Visual cards with success rate bars, model breakdown, error tracking",