session-handover v0.5: a cross-harness compaction semantics matrix

Description and use

session-handover v0.5 offers a cross‑harness compaction matrix, detailing retained and dropped session data when transferring between AI tools.

Problem

Users hand sessions between different AI harnesses and lose different pieces of state due to varying compaction behaviors.

Outcome

The tool provides a comprehensive matrix of compaction behaviors across multiple AI harnesses, enabling users to understand and mitigate state loss when transferring sessions.

Workflow

• Install the package with pip install session-handover
• Run session-handover compact-matrix to generate a cross-harness comparison
• Optionally output to a file with --out MATRIX.md
• Use --compare claude-code codex-cli for pairwise diff or --harness codex-cli for single harness audit

Evidence

v0.5 of session-handover widens the compaction audit from Claude Code to every harness I hand sessions to.

Source

It prints a cross-harness comparison: what triggers compaction, what mechanism it uses, what survives, what gets dropped, and — the part I actually use — the durable anchor where state should be pinned before compaction happens.

Source

Full report: session-handover compact-matrix --out MATRIX.md. Pairwise diff: --compare claude-code codex-cli. Single harness: --harness codex-cli.

Source