Jason Stedwell
446cd9a0ff
Three independently useful changes (IMPROVEMENT-PLANS #1/#3/#7), no schema changes: - load --brief: token-budgeted cold-start digest (facts full, last-10 observations, scope+freshness, last session's key sections, agent-log lines, inbox count; ECHO_LOAD_BUDGET ~8000 chars, lowest-priority-first trimming). SessionStart hook injects the brief form; /echo-load keeps the full dump. All load reads (+ the sessions listing, which also feeds the heartbeat fallback) fetched in parallel. - Offline capture durability: a fully-offline capture queues the WHOLE op as one semantic record; flush replays it through capture so routing/gate/aliasing re-run against the current index; a gate stop on replay is kept + flagged (needs_attention, surfaced by flush and load), never landed blind; update-path and ensure_daily_log writes ride safe_request; same-args captures dedupe. - session-end: one call, one lock — session log -> agent-log line -> reflect proposals (gate-aware) -> optional scope set -> heartbeat LAST as the commit marker; dry-run default; ECHO_NOW pins HHMM; validation runs before any write. Stop hook nudge names the command and recognizes it as reflected. - Fix: main() now catches the __main__ twin-module EchoError (via RuntimeError + .code) so helper-module errors exit with their intended codes, not tracebacks. +19 e2e checks; all suites green. Plans renumbered: MCP container is 2.2. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2.4 KiB
name, description, argument-hint, allowed-tools
| name | description | argument-hint | allowed-tools |
|---|---|---|---|
| echo-reflect | Reflect on this session — extract durable memories and propose them for one-tap capture | [optional focus, e.g. 'just decisions'] | Bash(python3 *echo.py*), Bash(python *echo.py*), Bash(py -3 *echo.py*), Bash(ls /sessions/*) |
Use the echo-memory skill to run session reflection (H5). Scan this conversation for things worth remembering across sessions, then propose them — don't write blindly.
- Extract durable items from the conversation: new facts, preferences, decisions,
commitments, people/companies/projects introduced, and anything the operator said to remember.
Skip the ephemeral. Anchor relative dates on the conversation's
currentDate. - Emit a JSON array of proposals (one per item), each:
{"title","kind","body","aliases","tags","sources","confidence"}—kind∈person, company, concept, reference, meeting, project, area, semantic, episodic, working, skill, decision; set"inbox": truewhen the home is genuinely unknown;confidence0–1 (items below 0.6 are dropped — send those to the inbox instead). Write the array to a file with the Write tool (cross-platform; no heredoc). - Preview, then apply. Dry-run first (writes nothing) and show the operator the plan; only apply after they confirm.
ECHO="${CLAUDE_PLUGIN_ROOT}/skills/echo-memory/scripts/echo.py" # python3 (Windows: python / py -3)
[ -f "$ECHO" ] || ECHO=$(ls /sessions/*/mnt/.remote-plugins/*/skills/echo-memory/scripts/echo.py 2>/dev/null | head -1) # CoWork sandbox fallback
python3 "$ECHO" reflect proposals.json # dry-run: validate + classify + preview
python3 "$ECHO" reflect proposals.json --apply # write — routes each via capture (indexed, linked, logged)
reflect dedups every proposal against the entity index (so it shows create-vs-update),
skips below-confidence items, and routes inbox proposals to the capture inbox. Each
applied item goes through the normal capture path — canonical frontmatter, auto-linking,
and the recall index — and the writes are lock-guarded.
Finishing the session? Prefer the one-call bundle — python3 "$ECHO" session-end bundle.json --apply — which applies the reflect proposals AND writes the session log,
Agent Log line, optional scope switch, and the heartbeat (last, as the commit marker)
together. See the echo-memory skill's Session Logging section for the bundle shape. $ARGUMENTS