This release fixes issues for SREs watching stability and regressions.
✓ No known CVEs patched in this version
Topics
+14 more
Summary
Bug fixes and stability improvements in Agent Sessions.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Low |
Shows real token throughput (e.g., `412K tk/h`) for Codex sessions without a 5‑hour budget. Shows real token throughput (e.g., `412K tk/h`) for Codex sessions without a 5‑hour budget. Source: llm_adapter@2026-07-14 Confidence: high |
— |
| Bugfix | Medium |
Displays "no limit" when OpenAI removes Codex 5‑hour rate‑limit window. Displays "no limit" when OpenAI removes Codex 5‑hour rate‑limit window. Source: llm_adapter@2026-07-14 Confidence: low |
— |
| Bugfix | Low |
Shows "can't verify" when provider usage data cannot be confidently interpreted. Shows "can't verify" when provider usage data cannot be confidently interpreted. Source: llm_adapter@2026-07-14 Confidence: high |
— |
Full changelog
What's New in 4.4
Highlights:
- Codex usage keeps working when OpenAI pauses the 5-hour limit. OpenAI temporarily removed Codex's 5-hour rate-limit window (it's gone from the Codex app too), which left the Quota Meter mislabeling your weekly usage as "5h" with the wrong reset. Agent Sessions now detects this automatically: the 5h line reads a calm "no limit", your weekly usage stays accurate, and everything snaps back on its own if OpenAI restores the 5h window.
- An honest Session Runway for Codex. With no 5-hour budget to measure against, each active Codex session now shows its real token throughput (e.g.
412K tk/h) instead of a burn rate scaled to the wrong window — a true, comparable read of what's burning right now. It returns to the familiar 5h "m/h" once the window is back.
Bug Fixes:
- New format guardrail: if a provider changes its usage data in a way Agent Sessions can't confidently interpret, the meter now shows a clear "can't verify" instead of displaying a wrong number.
Full release notes: https://github.com/jazzyalex/agent-sessions/releases/tag/v4.4
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About Agent Sessions
Local-first macOS app to browse, search, analyze, and resume supported AI coding-agent session history across Codex, Claude Code, OpenCode, Cursor Agent, Hermes, OpenClaw, Copilot CLI, and more.
Related context
Related tools
Beta — feedback welcome: [email protected]