Files
echo/echo-memory.plugin.src/skills/echo-memory/scripts/echo_session.py
T
Jason Stedwell b4e923c2e7
Build and Push Docker Image / build (push) Successful in 14s
2.3.0 — the index train: local-first recall index, incremental sweep, stemming + alias expansion
One schema-bump release (recall-index schema 3, entity-index schema 2; old
recall indexes rebuild automatically, no vault migration):

- Local-first recall index: the live BM25 index lives in the machine state dir
  (keyed by endpoint hash); capture's upkeep is a zero-network atomic file
  write, no advisory lock — replacing the O(vault) GET/PUT-whole-index round
  trip per write. The vault copy is a snapshot (sweep + session-end) used to
  seed fresh machines / catch up after another client swept
  (ECHO_RECALL_SYNC_HOURS, default 24). The read path never PUTs the vault.
- Incremental sweep: entity + recall meta carry 16-char content hashes;
  `sweep --fast` fetches only new/gone/hash-missing notes plus a rotating
  weekday shard (--all-shards forces everything); deletions drop from both
  indexes; index-only so no --apply gate. `load` auto-runs it past
  ECHO_FAST_SWEEP_DAYS (7); doctor reports index freshness. Obsidian-side
  edits now reach the indexes without manual maintenance.
- Stemming + alias expansion: echo_stem.py (conservative Porter-lite, unit-
  tested families + over-stemming guards) applied at index AND query time;
  a query fuzzy-matching an entity folds its title/alias vocabulary into the
  BM25 query at half weight — expansion can only boost docs containing the
  terms. capture hashes the note's FINAL content (auto-link reordered first).

Eval gold set 8 -> 14 queries (6 paraphrases): recall@5/MRR 1.00/1.00 vs
keyword baseline 0.75/0.79. +3 unit tests, +10 e2e; test harnesses now isolate
ECHO_STATE_DIR. All seven suites green.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-29 00:08:48 -05:00

178 lines
8.1 KiB
Python

#!/usr/bin/env python3
"""echo_session.py — the session-end bundle: one call ends a session correctly. [2.1.0]
Ending a substantive session used to take four-plus separate invocations (session-log
PUT, Agent Log append, heartbeat PUT, optional scope set, optional reflect apply) —
a cost per session, and a partial failure left broken orientation state (log written
but heartbeat stale). This verb does all of it in one call, under ONE advisory-lock
acquisition, in a fixed order with the heartbeat written LAST as the commit marker:
a failure part-way leaves the previous pointer intact, never a dangling one.
Bundle shape (JSON object):
{
"slug": "echo-mcp-spec", # required, kebab-case
"log_body": "<full session-log markdown, frontmatter included>", # required
"agent_log_line": "- 2026-07-28: ...", # optional; derived when omitted
"scope": "new scope text", # optional -> scope set
"reflect": [ { ...PROPOSAL_SCHEMA... } ] # optional -> routed via capture
}
Dry-run by default (previews the whole plan, reflect included); --apply writes.
Times: the filename HHMM comes from $ECHO_NOW (HHMM) else the local clock; the date
from ECHO_TODAY via echo.today(). Offline: every step rides the offline queue, so a
session end during an outage queues durably instead of failing.
CLI: echo.py session-end <bundle.json> [--apply]
"""
from __future__ import annotations
import datetime as dt
import json
import os
import re
import sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).resolve().parent))
import echo # noqa: E402
SESSION_RE = re.compile(r"^\d{4}-\d{2}-\d{2}-\d{4}-[a-z0-9-]+\.md$")
SLUG_RE = re.compile(r"^[a-z0-9][a-z0-9-]*$")
def _hhmm() -> str:
v = os.environ.get("ECHO_NOW", "").strip()
if v:
if not re.match(r"^\d{4}$", v):
raise echo.EchoError(f"session-end: $ECHO_NOW must be HHMM, got '{v}'", 2)
return v
return dt.datetime.now().strftime("%H%M")
def validate(bundle: dict) -> tuple[str, str]:
"""Return (session_path, agent_log_line) or raise EchoError(2). Validation runs
BEFORE any write — a bad bundle writes nothing at all."""
if not isinstance(bundle, dict):
raise echo.EchoError("session-end: bundle must be a JSON object", 2)
slug = str(bundle.get("slug", "")).strip()
if not SLUG_RE.match(slug):
raise echo.EchoError(f"session-end: slug must be kebab-case, got '{slug}'", 2)
if not str(bundle.get("log_body", "")).strip():
raise echo.EchoError("session-end: log_body is required (the full session-log markdown)", 2)
reflect = bundle.get("reflect")
if reflect is not None and not isinstance(reflect, list):
raise echo.EchoError("session-end: reflect must be a JSON array of proposals", 2)
fname = f"{echo.today()}-{_hhmm()}-{slug}.md"
if not SESSION_RE.match(fname):
raise echo.EchoError(f"session-end: derived filename '{fname}' violates the "
"canonical YYYY-MM-DD-HHMM-<slug>.md form", 2)
path = f"_agent/sessions/{fname}"
line = str(bundle.get("agent_log_line") or "").strip() \
or f"- {echo.today()}: session logged [[{path[:-3]}]]"
return path, line
def session_end_op(bundle: dict, apply: bool = False) -> dict:
"""Core session-end (Phase 0): validate -> plan -> (apply). Returns an envelope
(plan rows + per-step results); never prints to stdout — helper chatter from the
underlying verbs routes to stderr. Raises echo.EchoError(2) on a bad bundle,
BEFORE any write."""
import contextlib
import echo_output
import echo_reflect
path, line = validate(bundle)
scope = str(bundle.get("scope") or "").strip()
proposals = bundle.get("reflect") or []
valid, errors = echo_reflect.validate(proposals)
rows: list[dict] = []
if valid:
echo_reflect.classify(valid)
rows = [{"action": p.get("_action"), "kind": p.get("kind"),
"title": p["title"], "path": p.get("_path")} for p in valid]
data = {"path": path, "agent_log_line": line, "scope": scope or None,
"reflect_rows": rows, "reflect_errors": errors,
"dry_run": not apply, "steps": {}}
if not apply:
return echo_output.envelope("session-end", data)
import echo_concurrency
import echo_ops
steps: dict[str, str] = {}
with echo_concurrency.vault_lock(), contextlib.redirect_stdout(sys.stderr):
# 1. The session log itself. A hard failure here aborts the whole bundle —
# nothing after it (including the heartbeat) runs, so orientation state
# can never point at a log that was never written.
echo.cmd_put(path, echo.temp_file(str(bundle["log_body"]).encode("utf-8")))
steps["session_log"] = "ok"
# 2. Agent-log line (best-effort by contract; queues itself when offline).
echo_ops.ensure_daily_log(line)
steps["agent_log"] = "ok"
# 3. Reflect proposals through the normal capture path (gate-aware).
if valid:
gated = 0
for p in valid:
if p.get("_action") == "error":
continue
env = echo_ops.capture_op(
p.get("kind"), p["title"], body_text=p.get("body") or "",
aliases=p.get("aliases") or [], sources=p.get("sources") or [],
tags=p.get("tags") or [], date=p.get("date"),
domain=p.get("domain", "business"),
inbox=bool(p.get("inbox")) or not p.get("kind"))
gated += 1 if env.get("action") == "duplicate-gate" else 0
steps["reflect"] = f"{len(valid) - gated}/{len(valid)} applied" \
+ (f", {gated} gated (re-propose with --merge-into)" if gated else "")
else:
steps["reflect"] = "skipped (none)"
# 4. Scope switch (optional).
if scope:
echo.cmd_scope("set", scope)
steps["scope"] = "ok"
else:
steps["scope"] = "unchanged"
# 5. Heartbeat LAST — the commit marker for the whole bundle.
echo.cmd_put("_agent/heartbeat/last-session.md",
echo.temp_file(f"{path} @ {echo.now_iso()}\n".encode("utf-8")))
steps["heartbeat"] = "ok"
# Index maintenance (2.3), NOT part of the bundle contract: push this
# machine's local recall index to the vault snapshot so other machines
# can seed/catch up. Best-effort — a failure never taints the bundle.
try:
import echo_recall
rix = echo_recall._load_local()
if rix and rix.n_docs:
rix.built = rix.built or echo.now_iso()
echo_recall.save_snapshot(rix)
steps["recall_snapshot"] = "ok"
except Exception: # noqa: BLE001
steps["recall_snapshot"] = "skipped"
data["steps"] = steps
return echo_output.envelope("session-end", data)
def session_end(bundle: dict, apply: bool = False) -> int:
"""CLI wrapper: same plan/summary text as before; envelope logic in session_end_op."""
env = session_end_op(bundle, apply=apply)
for e in env["reflect_errors"]:
print(f"skip: {e}", file=sys.stderr)
print(f"session-end plan ({'APPLY' if apply else 'dry-run'}):")
print(f" 1. session log -> {env['path']}")
print(f" 2. agent-log line: {env['agent_log_line']}")
rows = env["reflect_rows"]
if rows:
print(f" 3. reflect: {len(rows)} proposal(s)")
print("\n".join(f" {r['action'] or '?':7} | {('-' if r['action'] == 'inbox' else r['kind'] or '?'):9} "
f"| {r['title']} -> {r['path'] or '?'}" for r in rows))
else:
print(" 3. reflect: (none)")
print(f" 4. scope set: {env['scope']!r}" if env["scope"] else " 4. scope: (unchanged)")
print(f" 5. heartbeat -> {env['path']} @ <now> (written LAST — the commit marker)")
if env["dry_run"]:
print("\nsession-end: dry-run — re-run with --apply to write.")
return 0
print("\nsession-end: done — "
+ "; ".join(f"{k}: {v}" for k, v in env["steps"].items()))
return 0