Skip to content

tally session

Cross-harness portable-agent-log: export, move, and verify coding sessions across machines and harnesses (operator-blind, context-level)

usage
tally session <COMMAND>

Extract the current harness session into the encrypted log as a canonical portable context (task + acceptance + plan + files pointer), then auto-push it operator-blind to your other machines

usage
tally session export [OPTIONS]
--harness <HARNESS>
Source harness: claude-code | pi | codex, or an installed community adapter name (tally adapter list) [default: claude-code]
--cwd <CWD>
Project directory of the session (default: current directory)
--session <SESSION>
Explicit session file path (default: newest session for the cwd)
--no-sync
Skip the auto-push after export

Materialize a stored portable context into a harness’s native session store so the harness resumes it (claude --continue / pi --session)

usage
tally session materialize [OPTIONS] --into <INTO>
--into <INTO>
Target harness: claude-code | pi | codex, or an installed community adapter name (tally adapter list)
--cwd <CWD>
Project directory to resume in (default: current directory)
--seq <SEQ>
Log seq of the context (default: newest portable_ctx)
--no-sync
Skip the auto-pull before materializing

Print the digest (or raw JSON) of a stored portable context

usage
tally session show [OPTIONS]
--seq <SEQ>
Log seq of the context (default: newest portable_ctx)
--json
Print the raw canonical JSON instead of the digest

Verify the repo against the context’s acceptance criteria: independent of the harness’s self-report (exit 0 iff every criterion is met)

usage
tally session verify [OPTIONS]
--seq <SEQ>
Log seq of the context (default: newest portable_ctx)
--repo <REPO>
Repository to verify (default: current directory)
--judge <JUDGE>
Judge command template for criteria without a check_cmd; must contain {PROMPT_FILE}. Default: pi on openai-codex/gpt-5.5
--no-judge
Disable the model judge (mechanical check_cmd criteria only)