Commit Graph

12 Commits

Author SHA1 Message Date
Jason Stedwell b4e923c2e7 2.3.0 — the index train: local-first recall index, incremental sweep, stemming + alias expansion
Build and Push Docker Image / build (push) Successful in 14s
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
Jason Stedwell 227e26c8db 2.2.0 — echo-mcp: the containerized MCP server
Build and Push Docker Image / build (push) Successful in 23s
ECHO as 14 typed MCP tools (streamable HTTP, stateless JSON, bearer auth, open
/health) wrapping the 2.1.1 *_op cores in-process:

- mcp-server/app.py: FastMCP app; duplicate gate + offline queueing surface as
  DATA (merge_into/force are parameters, never blind retries); recall packs
  excerpts into budget_chars by score; get_note is traversal-guarded with
  section/max_chars; patch_note enriches invalid-target errors with the note's
  actual headings; log_session wraps the session-end bundle (heartbeat-last);
  ECHO_MCP_TOOLS=core exposes only the six daily drivers; all MCP writes
  serialize in-process; startup fails fast on missing env.
- Dockerfile (legacy format — no BuildKit on the CI runner), python:3.12-slim,
  healthcheck probes 127.0.0.1; .dockerignore keeps the context lean.
- .gitea/workflows/docker-build.yml: standard image build; PORT redeploy
  trigger targets the echo-mcp container explicitly (repo name is echo).
- deploy.unraid.yml: br0/auto-IP, /data volume, vault adjacency
  (ECHO_BASE=http://10.2.0.35:27123), secrets as SECRET: refs.
- SKILL.md: prefer the echo_* tools when the connector is present; CLI recipes
  stay as the fallback. Spec header marked BUILT (tool count corrected to 14).
- eval/test_mcp_server.py: e2e over real streamable HTTP (health/auth/
  initialize/tools-list + capture->gate->merge->recall->log_session); skips
  cleanly when the SDK is absent. All seven suites green.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 23:01:47 -05:00
Jason Stedwell e7792003a7 2.1.1 — MCP Phase 0: every high-level op returns an envelope (return-not-print)
Internal refactor per docs/MCP-SERVER-SPEC.md §4; CLI output and exit codes
unchanged (wrappers reproduce them from the envelopes):

- echo_ops: capture_op/resolve_op/link_op — duplicate gate and offline queueing
  are data (action: duplicate-gate + candidates; queued: true); the --json
  stdout-swallow hack is deleted (helper chatter -> stderr inside the cores);
  capture_op takes body_text= directly (the MCP path, no temp file).
- echo_recall.recall_op — one structured result backs prose and --json.
- echo_triage.list_op/route_op, echo_reflect.apply_op,
  echo_session.session_end_op — call capture_op internally, count gate outcomes
  from envelopes.
- echo.scope_show_op/scope_set_op/load_op (+ shared _load_gather), and
  echo_doctor.run_op (checks as data).

New eval/test_ops_api.py asserts the contract for every core: envelope shape
AND stdout purity (a stray print would corrupt an MCP response stream). All six
suites green. The 2.2 server build now starts directly at the app layer.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 22:51:33 -05:00
Jason Stedwell 446cd9a0ff 2.1.0 — quick-wins train: brief load, offline-durable capture, session-end verb
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>
2026-07-28 22:34:42 -05:00
Jason Stedwell fb407d606c Add the 1.6.0 lint regression test (missed in the release commit staging)
Seeds archive/notes/README.md and asserts vault_lint flags retired-path —
fails against the pre-1.6.0 linter, passes with the retired-first check.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 21:59:39 -05:00
Jason Stedwell 993abdc846 Retire ROADMAP-1.0; rewrite run_eval.py as current-version metrics harness
Knocks two items off ROADMAP-2.0 (§4 eval refresh, §5 roadmap retirement):

- run_eval.py: the stale 0.6-vs-0.7 A/B is replaced (old version in git
  history) with a four-part current-version eval against the mock —
  retrieval (hybrid+priors vs keyword/entities-only baseline: R@5 1.00
  vs 0.75, MRR 1.00 vs 0.75, session/journal queries 2/2 vs 0/2,
  freshness top-1 correct vs wrong), dedup (0 dupes gate-on vs 3
  gate-off, 0 false blocks), write safety (0 silent failures across 4
  fault scenarios), durability (3/3 offline writes queued+landed, 0
  lost, 0 re-flush dupes). Results in eval/results/latest.json.
- README: metrics table published; repo-layout eval descriptor updated.
- eval/README: new harness documented; A/B framing marked historical.
- ROADMAP-1.0.md removed (fully shipped; story lives in the README
  version table + git history); dangling docstring pointer fixed in
  echo_concurrency.py; ROADMAP-2.0 checkboxes ticked.

All suites green; artifact rebuilt (1.5.1, docstring-only source change).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-03 13:30:01 -05:00
Jason Stedwell 3b6c3053cb ver 1.5.1 — duplicate-gate precision (common tokens, cross-kind)
Live 1.5.0 use caught the gate blocking a decision note over the single
vault-common token "echo" (min-normalized overlap gives any one-token
entity a 1.0 score). New echo_index.gate_candidates() + token_df():

- gate blocks same-kind candidates only; cross-kind name collisions
  (a decision titled after its project) warn instead of blocking
- a lone shared token blocks only when unique to that entity (df == 1);
  multi-token overlaps still block

fuzzy_candidates (advisory warnings) and exit-76/--merge-into/--force
semantics unchanged. +3 offline unit tests, gate e2e cases restructured
+2 new; verified live both directions. All suites green.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-03 13:03:07 -05:00
Jason Stedwell be3fd36ebf ver 1.5.0 — six-improvement pass: retention, routing, self-firing memory
1. capture-update keeps the whole body (was truncating to first line)
2. frontmatter completeness: kind-default status + kind-seeded tags at
   capture, fm create-or-replace, incomplete-frontmatter lint, sweep
   backfill (one data source: KIND_STATUS/KIND_REQUIRED_FM)
3. pre-write duplicate gate (exit 76, --merge-into/--force)
4. recall corpus + ranking: sessions/journal indexed (down-weighted),
   BM25 x freshness x status fusion, recall --json, index schema 2
5. session hooks: SessionStart auto-load, Stop reflection nudge
6. one-tap triage verb with processing-log audit; --json on read verbs

+22 mock end-to-end tests; all suites green. Docs current (README,
CHANGELOG, SKILL.md, commands, references, MAINTENANCE, eval README).
Drops tracked .DS_Store (gitignored); retires README-gretchen.md
(moved to gitignored dist/); adds the field report that drove item 2.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-03 12:57:52 -05:00
Jason Stedwell 151b962662 Documentation 2026-06-22 17:44:37 -05:00
jason 1c0c2ea66e ver 1.0 2026-06-22 09:27:36 -05:00
jason d404f6e96f ver 0.9 2026-06-21 11:46:54 -05:00
Jason Stedwell b299927117 ver-0.7 2026-06-19 21:12:14 -05:00