Commit Graph

9 Commits

Author SHA1 Message Date
df393152f6 docs: nomos agent code review — gaps and improvement plan
Full read-through of cmd/nomos/ (agent.go, store.go, main.go, continue.go,
assent.go, tasks.go). Findings, ranked:

- A1 (confirmed via runnable probe): isAssent/isTypedConfirmation use
  unpadded substring matching for assent/confirm words while negation uses
  word-boundary checks — "yes" matches inside "yesterday", "confirm" matches
  inside "confirmed" with no negation word covering contracted negatives
  ("haven't"). isTypedConfirmation gates DESTRUCTIVE actions specifically.
- A2: chatWith replays a session's ENTIRE message history every turn, no
  windowing/token budget — confirmed unbounded against a documented
  production case (70 tool calls, 106KB messages).
- A3: a live turn's tool-call history is lost entirely if the client
  disconnects mid-stream (single end-of-turn save using the same
  connection-tied, possibly-cancelled context) — resumeSession already has
  the fix pattern (incremental placeholder+update), handleChat doesn't use it.
- B1: zero recover() anywhere in cmd/nomos/internal/mcp/internal/httpapi —
  every explicitly-spawned goroutine (continuation worker, resumeSession,
  executeApprovedViaAPI, sse listeners) crashes the whole process on panic.
- B2: auto-continuation processes its batch sequentially, one full LLM turn
  at a time, undercutting this session's own concurrency work on exactly the
  path autonomous tasks depend on most.
- B3: no terminal state for a permanently-failed auto-continuation.
- C1: nomos's own gateway (port 8092, directly published + mesh-reachable)
  has ZERO authentication on any endpoint — chat, session read/delete,
  chat-assent approval of gated executions, all open to anyone on the LAN.
- D1-D3: dead code (isTaskTool unused), N+1 query in recordTouched, no
  validation on complete_task's outcome enum.
- E: zero automated tests for agent.go/store.go/main.go/tasks.go — including
  today's new safety-critical logic (session-scoped windows, mcpClientPool,
  proposePlan's append-vs-replace), verified only by live manual testing.
- F1: tool list + fleet snapshot re-fetched every turn (minor).

Prioritized implementation order in the doc: A1 → C1 → B1 → B2 → A3 → D1-3 →
A2 → B3/F1, tests landing alongside each fix rather than as a deferred pass.

Also archives the now-fully-shipped concurrent-task-execution plan to done/
(all 3 required fixes deployed this session; fix 4 explicitly deferred per
its own recommendation).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-11 19:47:17 +02:00
6932eb5eed docs: plan concurrent task execution; archive completed tasks plan
New plan grounds three concurrency issues found by tracing the actual code
(not assumed): the assent/destructive windows are keyed by agent id only
(no session dimension), so an approved plan in one task can auto-run
unapproved actions in a concurrently-running task; nomos shares one
mutex-guarded MCP client across all sessions, so a single slow `run` call
serializes every other task's tool calls behind it; and chat.ts's SSE
callback has no session guard, so switching tasks mid-stream lets the
backgrounded task's events corrupt whatever's now displayed. Proposes
session-scoping the windows (critical/first), a frontend stream guard
(contained/second), a per-session MCP client pool (throughput/third), and
an optional concurrency cap (deferred pending real usage data).

Also archives the goal-oriented-chat-control-panel plan to done/ — all 7
phases shipped and are live in production (SHA e30813a) — fixing its
internal relative links for the new depth and pointing forward to the new
concurrency plan as follow-up hardening.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-11 18:14:35 +02:00
ef5a92269b docs: reconcile plans/ status against actual code state
Audited all 10 active plan docs against the codebase (not just commit
titles). 5 were fully shipped and stale-tagged "Planned"/"In Progress" —
moved to done/ with verification notes. The other 4 got corrected
Planned→In Progress status plus concrete remaining-gap notes so the next
pass doesn't re-derive what's already done.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-11 11:42:26 +02:00
0d29b1db81 fix: move completed signal-triggers plan to done/, add missing liveness-drift to index, add plan-consistency lint checks 2026-07-09 10:47:39 +02:00
3ea43adcfd fix: repair 5 MCP analysis tools with SQL errors + seed entity_status rows
Some checks failed
ci / build-test (push) Has been cancelled
ci / docker-build (push) Has been cancelled
- get_event_timeline: event_type/actor/message → type/source/data::text
- get_blast_radius: add JOIN entities for slug column
- get_state_snapshot: remove nonexistent disk_usage_pct, drift_count
- get_change_history: timestamp/actor_label/details → ts/actor_id::text/detail
- seed: upsert entity_status rows during inventory ingest (was empty, causing INNER JOIN on get_health_summary to return nothing)
2026-07-08 12:27:25 +02:00
e148c7a981 move 5 completed plans to plans/done/
Some checks failed
ci / build-test (push) Has been cancelled
ci / docker-build (push) Has been cancelled
- Consolidate Oikos on mac-mini (2026-07-06)
- Client lifecycle in Go (2026-07-07)
- Comprehensive audit & next steps (2026-07-07)
- DB as source of truth (2026-07-07)
- MCP tool completion (2026-07-07)

Paths fixed in index.md to reflect planes/done/ locations.
Active plans remaining: Prometheus LXC (Planned), implementation audit (Active).
2026-07-08 11:30:54 +02:00
6b51c83b82 plans: mark TRMNL and wiki-hq adoption as done, move to plans/done/ 2026-07-07 21:06:58 +02:00
4efddb8bed docs: fix pre-existing broken links surfaced by docs-lint
Problem: docs-lint (added in the wiki-hq reorg) surfaced 126 broken relative
links that predated this session — a container rename, incident/plan docs
that moved into archive/done subfolders without their inbound links being
updated, and a handful of relative-depth bugs in files nested under
containers/archive/ and plans/done/.

Fixes applied, by category:
- 124-authentik.md -> 106-auth-outpost.md (container was renamed; ~40 refs).
- investigations/{2026-04-21-hubris-crash-loop,2026-05-31-authentik-vps-migration}.md
  -> archive/ prefix (both moved to investigations/archive/ previously).
- plans/{2026-06-01-slate-ax-to-sodola-migration,2026-06-04_130000-deprecate-claudio-bot,
  2026-06-25-yuvomi-deployment}.md -> plans/done/ prefix.
- Depth bugs in files nested one level deeper than their siblings assumed
  (investigations/archive/*, knowledge/wiki/containers/archive/*,
  plans/done/*) — corrected relative-path depth.
- Destroyed containers with no surviving page (126-plato) delinked to the
  containers/index.md archaeology row instead of a 404.
- ludo-mini.yaml -> strong.yaml (host was renamed, same physical machine).
- netbird-vps.md (no narrative page exists) -> netbird-vps.yaml (substrate
  record, matching the existing convention for hosts without a wiki page).
- runbook-dpkg-interrupted.md refs -> .agents/skills/runbook-dpkg-interrupted/SKILL.md
  (missed in the phase-4 runbook move because the referencing files used a
  bare filename, not a runbooks/ prefix).
- One dangling forward-reference to a never-written investigation delinked
  to the actual incident record it was describing.

Left alone: two links in knowledge/wiki/containers/101-jellyfin.md into
devops/homelab-authentik-admin/ — an intentional reference to a sibling repo,
not present in this checkout.

Verification: broken-link count 126 -> 2 (real remainder is the cross-repo
reference above); gen-topology.py --check still exit 0; build_host_files.py
still idempotent; all inventory.yaml doc_page targets still resolve.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-06 17:53:35 +02:00
fd35b48c8d Phase 1-4: full doc reorg
Phase 1 — fix stale state after strong migration (Phase 1+2, 2026-07-05)
  - README: corrected IPs (jellyfin 206→246, arriman 132→245, etc.),
    added missing containers (128 trmnl, 129 house, 133 seanime, 134 romm,
    124 authentik), updated last-refreshed date, added strong host context
  - containers/101-jellyfin.md: IP 206→246, host hubris→strong, mount
    /mnt/library→/mnt/media_local, GPU 760M→680M+RX7600, privilege→priv
  - containers/118-elementsynapse.md: IP 239→242, added Host: strong
  - containers/122-arriman.md: IP 132→245, mount→/mnt/media_local, added Host
  - containers/129-house.md: IP 212→244, added Host: strong
  - containers/130-grimmory.md: IP 213→247, mount→/mnt/media_local, added Host
  - containers/121-caddy.md: fixed site list (books→grimmory, removed auth→VPS,
    added house, roms, teddy, trmnl)
  - hosts/strong.md: updated At-a-glance to reflect 7 LXCs hosted
  - containers/123-claudio-bot.md, 127-mule-photos-new.md: archived to
    containers/archive/ (were destroyed LXCs with living pages)
  - inventory.yaml: verified correct — no changes needed

Phase 2 — structural cleanup
  - infrastructure/index.md: one-page overview of all cross-cutting systems
  - runbooks/: moved runbook-budget-from-csv.md and runbook-dpkg-interrupted.md
    from operations/ with YAML frontmatter added
  - plans/done/: moved 4 completed plans out of active view; updated index
  - vms/index.md: added VM index page

Phase 3 — navigation & discoverability
  - GLOSSARY.md: term definitions (Authentik, Caddy, LXC, VAAPI, etc.)
  - README: added table of contents, links to glossary + infrastructure index
  - investigations/: archived 2 resolved cases (crash-loop, authentik-migration)
    to investigations/archive/; updated index with active vs archived sections

Phase 4 — ongoing discipline
  - CONTRIBUTING.md: documented same-session update rule with explicit checklist
  - README: replaced full LXC table with summary + link to containers/index.md
    (single source of truth; de-duplication)
2026-07-06 00:46:27 +02:00