admin/Codex-Launcher---Any-AI-Porovider
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

v3.11.5: token-aware compaction, vision filter, universal adaptive compaction, smart-continue text detection

Browse Source
This commit is contained in:
Roman | RyzenAdvanced
2026-05-26 16:14:05 +04:00
Unverified
parent 028185652d
commit b029e7cb5e
9 changed files with 684 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
src/codex_launcher_lib.py
View File

@@ -83,14 +83,24 @@ model_catalog_json = ""
"""
CHANGELOG = [
("3.11.5", "2026-05-26", [
"Token-aware compaction: fixes context_length_exceeded on small-context models (25 items × 1600 tokens)",
"Proactive compaction triggers on token count (>80% model limit), not just item count",
"Universal adaptive compaction: removed crof.ai-only gates, all providers get compaction",
"Vision model detection: strips images for non-vision models, keeps for vision-capable ones",
"Per-model token limit learning from context_length_exceeded error messages",
"Compaction aggression levels: normal vs extreme when tokens > 1.5× model limit",
"Smart-continue text-tool detection: triggers on tool-call text patterns, not just function_call_output",
"Active endpoint sync: GUI auto-removes stale endpoint references on startup",
]),
("3.11.0", "2026-05-26", [
"Merge cobra PR: concurrency semaphore (max 3), auto-continue for truncated text",
"SO_REUSEADDR on sticky port, proxy-stderr.log, stream diagnostics logging",
"Timeout/OSError handler sends response.failed SSE instead of silent drop",
"Restart Proxy button: only restarts proxy without killing Codex Desktop",
"Tool call argument normalizer: fixes Arguments→arguments, strips markdown wrapping",
"Smart-continue loop (2× retries): escalating nudges when model stops text-only mid-task",
"XML tool call extraction: parses <tool_call> patterns from text, injects as real calls",
"Tool call argument normalizer: fixes Arguments->arguments, strips markdown wrapping",
"Smart-continue loop (2x retries): escalating nudges when model stops text-only mid-task",
"XML tool call extraction: parses patterns from text, injects as real calls",
"Auto-continue + smart-continue ordered with skip guard to avoid double-firing",
"API key hot-reload with mtime tracking + /admin/reload + /admin/verify-key endpoints",
"GUI hot-reload: auto-refreshes proxy key on endpoint edit, verifies with upstream",