Skip to content

Agent Sessions

v4.4 Bugfix

This release fixes issues for SREs watching stability and regressions.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agentic-workflow ai ai-coding-agents anthropic claude-code codex
+14 more
codex-cli copilot-cli cursor-agent developer-tools hermes-agent local-first macos openai openclaw opencode session-history session-management transcript-search usage-tracking

Summary

Bug fixes and stability improvements in Agent Sessions.

Changes in this release

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

Track Agent Sessions

Get notified when new releases ship.

Sign up free

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.

All releases →

Related context

Beta — feedback welcome: [email protected]