Round 2 of the agent handoff dogfood showed that every multi-branch
operation required reaching past the CLI into curl: fork had no CLI
command, `smriti checkpoint create` always spawned a fresh session with
no way to attach to a forked one, and the compare endpoint returned
useless output (common_ancestor_commit_id was missing from the response,
and shared-set matching was exact-string so two agents phrasing the
same commitment differently showed zero overlap).
This ships the full CLI surface for multi-branch workflows plus the
backend fixes that make compare actually useful:
smriti fork <checkpoint-id> [--branch <name>]
smriti restore <checkpoint-id>
smriti compare <checkpoint-a> <checkpoint-b>
smriti checkpoint create <space> --session <session-id>
The compare endpoint now walks parent chains to compute a lowest
common ancestor (bounded to 1000 steps with a cycle guard) and returns
it on CheckpointDiff as an optional uuid. Shared-set matching uses a
lightweight lowercase + punctuation-strip + whitespace-collapse
normalization for keying, but returns the original A-side strings so
the output stays readable. Four new compare tests cover direct and
two-step LCA, null LCA for unrelated checkpoints, and normalized
shared-set matching. Existing compare tests still pass unchanged
because their data ("Use Redis" vs "Use Postgres") is distinct at any
sensible normalization level.
`smriti restore <checkpoint>` is a pure read — it renders any
checkpoint as a continuation brief matching `smriti state <space>`
shape. `smriti fork` derives the space from the checkpoint so the
user does not have to pass it separately. `--session` on checkpoint
create is purely additive: when absent, the existing auto-session
behavior is unchanged.
147/147 backend tests pass (143 pre-existing + 4 new).
Two rounds of agent-handoff dogfood testing surfaced that Smriti had no
way to delete spaces, sessions, or checkpoints via any surface. This
adds DELETE endpoints to the V2/V4 API, new CLI commands, and UI
affordances on the workspace overview and chat history panel so the
daily cleanup path does not require opening a Python shell.
Checkpoint delete refuses with 409 Conflict when child commits or
forked sessions reference the target, because silently orphaning them
would cause walk_ancestors to collapse lineage and forked sessions to
lose isolation. The refusal is escaped via ?cascade=true on the API,
--cascade on the CLI, and a two-step confirm with a dependents list
plus checkbox in the UI modal.
Space delete relies on the existing DB-level cascade chain from the
earlier commit/session/turn migrations — no new Alembic migration is
needed. Session delete cascades turn events but preserves commits
authored by the session, since commits are space-owned artifacts.
14 integration tests cover cascade correctness, 409 refusal, the
cascade escape hatch, cross-user 404s, subtree ordering, and
idempotency. Existing tests pass unchanged (143/143).
REPO_STRUCTURE now lists the cli/ directory and refreshes the API
version map to reflect that V2 is current and serves the CLI's read
path (with the full checkpoint schema). docs/API.md replaces the
"do not build against V2" guidance with a clear description of which
prefix is used for what.
Introduce a thin Python CLI that wraps the backend REST API. Seven
commands: space list, space create, state, checkpoint create,
checkpoint show, checkpoint list, checkpoint review. Reads piped
JSON on stdin for checkpoint create, prints a continuation-oriented
markdown brief for state. Supports --json on every command for
structured output.
Fixes a V2 schema drift where the commit response omitted
assumptions and artifacts, so the CLI can read full checkpoints
via the cleaner V2 single-resource endpoints. Updates README,
ARCHITECTURE, and DECISIONS to frame Smriti as a reasoning-state
backend with the chat UI and CLI as two clients of the same core.
Replace the auto-session landing behavior with a resume-focused
overview at /. When returning after a break, the root page now
shows the most recent checkpointed session as a Resume card with
its current objective and last checkpoint summary visible, plus
cards for other recent spaces. New sessions explicitly go through
/sessions/new instead of being created on bare /.
Surface a soft drift hint in the chat header when many turns have
passed since the last checkpoint (turn-count based, not semantic).
Add a Restore action to the checkpoint detail panel as a peer to
Review, so users can act on a checkpoint without leaving the
inspection flow. When review surfaces issues, show an inline
Continue from this checkpoint button so recovery is one click away.
Update README with restore UX, checkpoint review, assumptions,
and artifacts. Add when-to-use guidance. Sharpen problem statement
around drift and recovery. Update ARCHITECTURE with new checkpoint
fields and restore terminology. Add three new decisions to
DECISIONS.md. Document review endpoint and new fields in API docs.
Checkpoints can now hold attached artifacts — text content captured
from chat messages or added manually. Artifacts are included in
prompt context when a checkpoint is active, grounding reasoning in
actual content rather than just summaries. Add capture button on
messages, artifact management in checkpoint modal, and collapsible
artifact display in checkpoint detail.
Separate assumptions from decisions as a first-class checkpoint
field. Add review endpoint that surfaces reasoning consistency
issues: contradictions, hidden assumptions, resolved questions,
and unused entities. Extend draft extraction, prompt context,
and compare diff to include assumptions.
Rename mount/unmount flow to restore/exit restore. Add visual
restore boundary divider in chat timeline. Dim pre-restore turns
to make isolation visually obvious. Show contextual empty state
and one-time hint for restored context.
