dtoro
e055a7c6ce
Classifier now unwraps pct exec / qm guest exec / bash -c / sh -c / sudo
and env-var assignments before classification, so read-only inspection
wrapped in pct exec no longer escalates to config_mutation. curl GET
(default method, no -d/-F/-T/-o/>) is read-only. Eliminates the three
duplicate rclone sessions (a51e2086, 8acea2e3, cb8c8a4a) that bounced
off the classifier for the same goal.
New classify_command MCP tool: command-scoped preflight that returns the
exact risk class run would assign. Documented in SOUL.md with guidance
to pre-classify before run when the verdict is uncertain.
set_goal surfaces prior partial/failed sessions from the last 24h so the
agent picks up the thread instead of rediscovering it.
completeTask auto-closes in-flight plan steps (pending/running -> done
on success, skipped on partial/failure), so one-step plans no longer
need the per-step running->done dance right before completion.
Migration 021 adds blocker + closed_at to agent_sessions. completeTask
sets closed_at once and derives a structured blocker reason
(approval_timeout, user_abandoned, classifier_overreach, model_refusal,
tool_error, ...) from the last assistant message.
/sessions list now carries message_count, tool_call_count,
duration_seconds (server-side aggregates — no more N+1 transcript
fetches to audit a fleet). GET /sessions/{id} returns both metadata
and messages. New query params filter + paginate: outcome, status,
entity_id, blocker, since (RFC3339 or Go duration), cursor, limit.
Titles now prefer the goal when set; sessions without a goal fall back
to the first assistant text.
New GET /sessions/{id}/tool_calls flat view for audit scripts.
Plan: plans/2026-07-20-session-review-ten-sessions.md. VERSION 0.7.12 -> 0.7.13.
5.7 KiB
5.7 KiB
Plans
Pre-flight runbooks for planned changes. When a plan is executed, move it to
done/ and add changelog entries on affected node pages. If things
went sideways, open an investigation.
Active
| Date | Title | Status |
|---|---|---|
| 2026-07-05 | Oikos Prometheus LXC | Planned — not started |
| 2026-07-08 | Oikos gaps, broken things, and improvements | In Progress — security items (B1-B5) and doc drift (E) still open |
| 2026-07-08 | Control room web UI | In Progress — packaging/auth sections superseded by the Wails plan's Phase 0 (client/server split); M4 still open |
| 2026-07-08 | Liveness, drift, and UX cohesion | In Progress — Phase 5 deferred |
| 2026-07-10 | General gated execution: unlimited actions, gated by risk | In Progress — request_execution enum retired (60effcb); only auto-act revival (item 10) still open |
| 2026-07-11 | Nomos agent code review: gaps and improvement plan | In Progress — only C1 (unauthenticated nomos gateway) still open, deferred |
| 2026-07-14 | Activity gaps | In Progress |
| 2026-07-14 | Activity timeline | In Progress |
| 2026-07-17 | Codebase review, lint audit, and documentation maintenance | Report delivered — doc/tooling fixes applied; code refactors pending |
| 2026-07-18 | Session review: three recent sessions | Implemented in v0.7.12 — P0.1/P0.2/P1.3/P1.4/P1.5/P1.6/P1.8/P2.10; P1.7 and P2.9 deferred (retry cap covers) |
| 2026-07-20 | Desktop mascot ("Cluck") | Planned — not started |
| 2026-07-20 | Session review: past 10 sessions | Implemented in v0.7.13 — all P0/P1/P2 items landed |
Done
See done/ for executed plans:
Conventions
- File name:
YYYY-MM-DD-<slug>.md. Use the target date if known, otherwise the planning date. - Status:
Planned→In Progress→Done(move todone/on completion). - When done: add a changelog entry on every affected node page, then move the file to
done/. - Plans are append-only once execution starts — don't rewrite pre-flight intent after the fact.