ef762794e7d52acdaaf1c28c1840343aeb1cb47d
70 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
| 7a34d8c8a0 | 0.27.1 — flat Infisical keys (_), seed-secrets.sh in deploy, plist cleanup, .env strip | |||
| c9d506b0f8 | 0.27.0 — Infisical hardening: runtime refresh, audit logging, CLI verify/audit, startup verification, SSH host key verification, interface consolidation | |||
| 4e294b3630 |
0.22.0 — full MCP agent surface: 19 new tools, async run, session reliability
Stage 1 — Foundation:
- Target validation: iptables + systemctl/docker target-type gates
- Async run for long-running commands (sleep/wait/poll loops)
- audit_log.session_id plumbing (SQL, sqlcgen, 18 call sites)
Stage 2 — External agent observe (11 tools):
- get_dashboard_summary, get_ontology, list_checks, list_executions
- get_knowledge_revisions, get_knowledge_duplicates, get_knowledge_orphans
- list_knowledge_tags, list_entity_sessions, find_entities_by
- 3 resource templates: oikos://entity/{slug}, knowledge/{id}, execution/{id}
Stage 3 — Nomos reliability:
- complete_task(success) refused without verification (upgraded from warn)
- sessionHasPlan excludes replaced steps (forces propose_plan after reopen)
- Bash syntax validation in run() (rejects literal \n, flag-space typos)
- Scope gate in SOUL.md (ask before pivoting to unrelated subsystem)
Stage 4 — External agent act (9 mutation tools):
- ack_signal, resolve_signal, mute_signal, cancel_execution
- update_check, delete_knowledge, restore_knowledge
- merge_knowledge, rename_knowledge_tag
|
|||
| c3f478b8f8 |
v0.21.0: agent reliability overhaul — plan integrity, target validation, observability pipelines, learning loop
P0 — stop the bleeding: - prevent premature complete_task(success) when goal involves reachability - validate run targets: block host-only commands (qm/pct/pvesh) on LXC/VM - bump MCP client timeout 30s→120s to stop 'context deadline exceeded' P1 — fix the plan system: - add replaced_reason column to session_plan_steps (migration 030) - track WHY steps are replaced (wrong_diagnosis/scope_change/superseded/etc) - force fresh propose_plan on session resume (reopenSession marks old plan) P2 — cognitive guardrails: - SOUL.md scope-gate rule: ask before chasing unrelated subsystems - auto-upsert knowledge entry on every session close P3 — observability (all were empty/NULL): - populate agent_activity.token_count from LLM usage (was always NULL) - populate nomos_plan_executions linking executions to sessions - write plan_completion_rate metric on task close P4 — learning loop (all were empty/NULL): - auto-classify every run call → classifications table (was 0 rows) - auto-feedback on session close (was 0 rows) |
|||
| 1aaedf498a |
v0.20.0: thinking blocks, chat windows overhaul, scroll fix
Backend: - Add isThinking flag to agentEvent for text before tool calls - Separate thinking from response text in runChatTurn and continue.go - Persist thinking in a dedicated field in message content Frontend: - Add thinking field to MessageContent, ChatMessage, ChatTextEvent types - Create ThinkingBlock.svelte — collapsible block with brain icon - SSE handler moves text_delta content to thinking on isThinking flag - Render thinking block between tools and response in ChatThread - Fix chat window scroll reset on focus change (stable windowKeys order) - Remove redundant #key id wrapper in WindowLayer - Enlarge sidebar rail (24→32 default, 40→60 max) - Remove glyph from sidebar, square graph at top - Replace AgentTrace/ToolCallCard/UnifiedTimeline with TurnTrace/ToolLine |
|||
| 5b68bdc16c |
feat(nomos): chat working-visibility, message queue, generation-aware timeline
Make background/long/desynced turns visible and queueable, fixing the four
symptoms that survived the v0.15.0 chat reliability pass.
F1 - status-driven working signal (workspace.ts taskWorking/currentWorking =
streaming OR status in {planning,executing}). Drives the chat trace, indicator,
and activity spinner so a turn with no live stream (background resume, a dropped
SSE, an idle-close mid long turn) still looks alive.
F2 - operator messages sent during an in-flight turn are now QUEUED and
auto-run when the gate frees, replacing the "still finishing a previous step...
send it again" rejection. Per-session in-memory FIFO (messagequeue.go, capped at
20) drained one-at-a-time under the turn gate; a `queued` SSE event drives a
"Queued" hint. drainQueued releases via a per-iteration deferred closure so a
runChatTurn panic can't deadlock the session's gate.
F3 - SSE keepalive (12s `:keepalive` comment) in handleChat so 20-40s
inter-iteration gaps no longer trip a proxy/browser idle close (the desync root
cause). All SSE writes serialized through one mutex.
F4 - generation-aware activity timeline (only the last propose_plan renders;
superseded ones collapse to one "Earlier plan revised" marker; step-attribution
follows only the current generation) + debounced plan refetch on lifecycle
events so a missed plan.proposed self-heals.
Verified against the last session (23da10db: 6m33s turn, operator "status"
deferred at 19:48:05). go test ./cmd/nomos/ green (new messagequeue tests);
web vitest 72/72 (new F4 generation tests); vite build clean.
VERSION: 0.16.0 -> 0.17.0
|
|||
| 39e9227fdb |
feat(nomos): per-session turn serialization + chat reliability/UX fixes
The agent could run two turns for one session at once (a reconnect resumed
while the live turn was still going), and their interleaved tool calls
corrupted the activity panel, fabricated a confusing "parallel/nested"
sequence, and made tasks feel stuck/never-ending. Several UX gaps compounded it.
Turn serialization (F1):
- turnGate: at most one in-flight turn per session. Background resume paths
(continuation worker, idle sweep, answer-question, /resume, reconnect)
skip non-blocking when busy; the live chat path waits briefly then bails
cleanly instead of stacking a second turn.
- resumeSession returns whether it ran; continueSession marks an execution
"continued" only after a real run (review P0) so a busy-skip can't lose a
finished-execution result. Idle nudge bumps only after delivery (P1).
Connection state (F2/F3, web):
- humanize/bucket raw errors ("model connection dropped..."); one surface
per drop; a terminal task.status event clears stuck streaming/disconnected
state and dismisses the connection toast. Reconnect no longer spawns turns.
Streaming where you look (F4, web):
- live command output in the global activity timeline and in the inline
tool card (auto-opened, tail-pinned) -- not just the per-window rail.
Other (web): artifact/knowledge deep links (F5); step-first stable
"thinking" headline (F6); stable chat layout, no empty->content reflow (F7);
lazy event sync (P2.2); reconnect skips a terminal session (P2.1).
VERSION: 0.14.2 -> 0.15.0
|
|||
| 467589d78a |
fix(nomos): generation-relative plan seq + real activity timestamps
The plan recorded false history after a re-plan and the activity panel showed fabricated, churning timestamps. Two bugs compounding on one event stream. Plan drift (P0.1): - proposePlan seq is now 1..N per generation; (session,generation,seq) is the addressing key. The model's 1-based update_plan_step calls always map to the CURRENT plan after a re-plan, instead of resurrecting a superseded `replaced` row as done while the live work went unrecorded. - updatePlanStep resolves against MAX(generation); a stale/out-of-range seq returns errPlanStepNotFound (never touches a superseded generation). - getPlanSteps returns only the current generation by default; ?all=true keeps the audit/eval view (plan_generations assertion). - completeTask auto-close scopes to the current gen, stamps started_at, and emits one plan.step.finished per closed step so the panel converges instead of freezing on "running" after completion (P1.1). - propose_plan result enumerates step seqs; writeback detector matches "write back"/"writeback"/"upsert_knowledge" so a natural-language final step isn't doubled (P1.2). - migration 029 renumbers existing seq per generation + unique index. Activity panel (P0.2 / P1.1, web): - computeActivityLog uses the real message created_at for tool calls; live entries fall back to wall-clock frozen on first sight, killing the 3s poll churn. Steps use real started_at. - dropped plan-step events warn + count instead of a silent no-op. Tests: TestProposePlan updated; + generation-relative-seq and auto-close event-emission regression tests; + web activity purity/timestamp tests. VERSION: 0.14.0 -> 0.14.1 |
|||
| ce34cfeac7 |
feat(web+nomos): fix chat streaming reactivity, unified activity timeline, tool cards in chat
- fix(web): Svelte 5 identity-based reactivity broke text_delta streaming — immutable message objects in all three chat handlers so text streams live - feat(web): streaming cursor + inline status indicator merged into message flow - feat(web): expandable inline tool call cards in chat thread - feat(web): merge Plan + Event log into one backbone Activity timeline — filled status nodes, branch stubs, auto-scroll follow mode, per-session activityLog, compact for the rail - fix(nomos): add X-Accel-Buffering:no to /chat SSE (proxy buffering) - fix(nomos): plan step auto-close SQL param bug (store.go) - polish: timestamps, role labels, code copy button, table overflow, min window size, delete AgentIndicator/ActivityTimeline dead code |
|||
| e055a7c6ce |
feat(nomos): session-review improvements (P0/P1/P2 from 2026-07-20 audit)
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.
|
|||
| aed068de12 |
feat(web): redesign UI as an OS-style desktop shell
Replace the sidebar + hash-routed page shell with a desktop metaphor:
draggable app icons, apps opening as floating wmkit windows, a centered
"What should Nomos do?" task launcher, and a bottom taskbar showing all
open windows plus a system tray.
- New app registry ($lib/apps.ts) — adding an app is one entry, nothing
else to touch.
- New desktop shell components (Desktop, WindowLayer, DesktopIcon,
Taskbar, TaskLauncher) under $lib/components/desktop-shell/.
- Icon positions are a persisted, collision-avoiding grid ($lib/stores/icons.ts).
- Window layout persists across reloads (wmkit persist), with
drag-to-maximize, F6 window cycling, and now a right-click desktop menu
(cascade/tile/show desktop/reset icons) plus Cmd/Ctrl+Z undo/redo for
window moves, resizes, and closes.
- Taskbar buttons get a hover-close and self-correct their title once a
new task's real goal is known.
- New task windows (desktop launcher and the Tasks app's "New task"
button) open as a window, not a dialog, and hand off to the real
session window once the backend assigns an id.
- Fixed a real gap along the way: GET /sessions/{id} couldn't tell
"session deleted" from "session has no messages yet" (both returned
200 with an empty list) — cmd/nomos/main.go now checks existence and
404s, so a stale/persisted task window shows "Task not found" instead
of a misleadingly empty, live-looking chat.
- Test coverage for the new pure logic (icon placement/collision
avoidance, app registry id helpers) plus a vitest matchMedia polyfill
needed to import anything touching the theme store.
Deletes the now-superseded sidebar shell, MinimizedWindowsBar, and the
standalone Chat/EntityDetail pages (folded into the window layer).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
|
|||
| 544afae77f |
feat(nomos): retry cap, vm: targets, inspect_path, goal supersession, runbooks
Session-review implementation for the three sessions audited in
plans/2026-07-18-session-review-three-sessions.md. v0.7.11 → v0.7.12.
P0.1 — retry cap + investigate-before-retry (cmd/nomos/retrycap.go,
agent.go): after 3 identical failing run calls in a single turn, refuse
to dispatch the call again and return a directive to investigate *why*
(ps/strace/lsof) or surface the blocker. Per-turn scope so a fresh turn
after the operator responds can retry once more. Session 1e9c7691's 20+
identical chown retries (knfsd held a kernel lock on the exported NFS
dir) is the direct motivation.
P0.2 + P1.8 + P2.10 — SOUL.md guidance: hung command is not a failed
command (investigate before retry); ask before proposing a multi-step
migration; multi-goal sessions summarize the arc not just the last goal.
P1.3 — two new runbook entities in seeds/knowledge.yaml:
- nfs-exported-dir-mutation-hang (the knfsd fchownat lock procedure:
killall → exportfs -u → mutate → exportfs -a → verify)
- netbird-mgmt-oidc-race-after-upgrade (docker restart netbird-mgmt
after ~30s for the traefik/authentik OIDC race)
P1.4 — setGoal emits task.superseded event when prior goal is overwritten
by a different goal (store.go, TestSetGoal_SupersededEvent). Session
55927f0a had two set_goal calls with the first silently abandoned.
P1.5 — inspect_path MCP tool: runs mount/df/ls/stat for one path across
up to 8 targets in one parallel call, replacing the 15+ run-call
fact-gathering fan-out sessions 1 and 2 each spent on cross-target path
tracing (tools.go, server.go: inspectPathAcrossTargets, inspectOneTarget).
P1.6 — vm: target support in run via qm guest exec (no more SSH-hop
with nested quoting). Extracted shared resolveProxmoxHostSlug for
LXC + VM, with hosts-relationship fallback when attributes.host is
absent (server.go, tools.go). Session 55927f0a's SSH-hop workarounds
for vm:zimaos are the direct motivation.
Deferred (documented in plan): P1.7 (approval window auto-extend on
timeout) and P2.9 (long-running command PENDING detection) — both
addressed at lower cost by the retry cap. Session 3's poll-after-timeout
pattern already works; the cap protects against the failure mode.
|
|||
| 876f181068 |
fix(agent): don't auto-complete sessions with pending approvals
The auto-complete fired when the agent hit the P5 approval gate — it queued a config_mutation run for approval, the P5 gate blocked further runs, the turn ended, and auto-complete closed the session as 'partial'. The operator's approval would then land on a dead task. Fix: hasPendingApprovals check — if the session has any executions in pending_approval state, skip auto-complete. The session stays in 'executing' until the operator approves (or denies). VERSION 0.7.5 → 0.7.6 |
|||
| df24cae507 |
fix(agent): fully silent assent — no system notes, no chat_assent events
The len(pending)>0 path still injected a brief note saying 'execution(s) are now running' — the model saw this, thought work was being done for it, and no-op'd (finish_reason=stop, content_len=0). Same confusion as the len(pending)==0 case, just from the other branch. Fix: both assent paths are now fully silent. No system note at all. The model sees 'go ahead' in the replayed history and responds naturally. Also removed chat_assent tool_use/tool_result emit events. These were persisted in the transcript and confused the model on replay — it saw its own 'tool calls' (chat_assent) and thought it had already acted. VERSION 0.7.4 → 0.7.5 |
|||
| e4e426de7d |
fix(agent): auto-complete with partial outcome when writeback missing
The auto-complete safety net required hadEntityWriteback to be true, which meant sessions where the agent did the work but forgot to call update_entity_attributes stayed stuck in 'executing' forever. Relax: auto-complete fires if the agent did discovery (ran run), regardless of writeback. If writeback happened → success; if not → partial (honest: work was done but knowledge graph not updated). VERSION 0.7.3 → 0.7.4 |
|||
| ca2ff56a25 |
fix(agent): mark chat-assented executions as continued to prevent race
When the chat handler approves a pending execution via chat-assent, the execution completes in ~2s. The continuation worker detects the completed execution and calls resumeSession — while the chat handler is still processing 'go ahead'. Two concurrent LLM calls for the same session cause empty responses (finish_reason=stop) and race conditions. Fix: mark the execution as continued immediately after chat-assent grants it, so the continuation worker skips it. The chat handler will drive the continuation itself (the model sees 'go ahead' and executes the plan). VERSION 0.7.2 → 0.7.3 |
|||
| d6e180845c |
fix(agent): silent assent — stop injecting confusing system notes
The assent pre-processing injected verbose system notes ('the operator
approved... they are now running... you MUST continue...') on top of the
replayed user message ('go ahead'). The model saw both, latched onto
'now running', concluded the work was being done for it, and no-op'd
(finish_reason=stop, content_len=0) — leaving the session stuck in
'executing'.
Root cause: the model already sees 'go ahead' in the replayed history
(the user message is saved to the DB before chat() is called, and
getRecentMessages replays it). The system note was redundant AND
confusing — it told the model work was 'running' when it wasn't.
Fix:
- len(pending)==0 (plan-proposal approval): open assent window silently.
No system note. The model sees 'go ahead' and responds naturally.
- len(pending)>0 (actual pending executions): brief note naming the
specific execution IDs that were approved ('don't re-request those').
No 'continue the plan' directive — the model knows to continue.
VERSION 0.7.1 → 0.7.2
|
|||
| 7ef8446825 |
fix(agent+ui): whatsapp session audit — approvals, stuck indicator, stale execs
P1: add docker compose (logs|ps|top|config|images|port|cp) to read-only allowlist. docker compose logs was classified as config_mutation, causing individual approval cards for read-only inspection commands. P2: remove approval entries from activityLog. They were always status=running and never transitioned to done (the derived store builds from tool-call text, not execution status), causing AgentIndicator to latch onto a stale 'Approval: ...' entry and never clear — even after the session completed. P3: remove InlineApproval from Chat.svelte. The green 'Completed in 1s on lxc:...' boxes were noise in the chat stream. Approval UX belongs in the Operations page (already has it via Ops.svelte), not inline in the chat. P4: stale execution cleanup. Startup sweep (mark >1hr non-terminal as cancelled) + 5-min periodic sweep (mark >10min non-terminal as cancelled). 98 orphaned executions accumulated from eval testing (39 running from apt_upgrade:audit timeouts, 19 pending_approval, 3 approved). P5: refuse second config_mutation run when an approval is already pending for the session. Without this, the agent queues N individual approvals before the operator can respond — confirmed in session 20757eb9 (two approval cards for what should have been one plan-level approval). VERSION 0.7.0 → 0.7.1 |
|||
| d55bae17b9 |
fix(agent): broaden auto-complete to discovery+writeback path
The agent often skips update_plan_step bookkeeping (leaving steps pending/running) but still does the work + writeback. The strict allPlanStepsTerminal check missed these cases. Add path (b): if the agent did discovery (ran `run`) AND wrote back (update_entity_attributes/create_relationship), auto-complete. D.1 already enforces writeback before completion — if writeback happened, the work is done. |
|||
| e3b5fdc358 |
feat(agent): auto-complete tasks when all plan steps are terminal
The #1 remaining model reliability gap: the agent does the work (proposes plan, executes all steps, writes back) but forgets to call complete_task, leaving the session stuck in 'executing'. The eval showed 3/8 failures with this pattern. Fix: autoCompleteIfPlanDone — a structural safety net that fires at both chat exit paths (normal completion + maxIterations). If the session has a goal, the agent didn't call complete_task, and ALL plan steps are in a terminal state (done/failed/replaced/skipped/blocked), auto-complete with the agent's final text as the summary. Mirrors autoCompleteTrivialTask but for structured tasks where the work is provably done. Also: bump maxLLMRetries from 2 to 3 (complex multi-turn flows benefit from one more retry on empty responses). |
|||
| 3c3b12df5e |
fix(agent): directive assent notes + retry bump to fix empty responses
The assent system note said 'Do not re-request or call run again for these' — the LLM interpreted this as 'don't call run at all' and produced empty responses (finish_reason=stop, content_len=0) until retries were exhausted, leaving the session stuck in 'executing'. Fix: rewrite both assent notes (pending-approval path and pure-plan-approval path) to be directive about WHAT TO DO NEXT: call update_plan_step(running) then run for each remaining step. The 'don't re-request' guidance is now scoped to 'THOSE SPECIFIC' executions, not all run calls. Also bump maxLLMRetries from 2 to 3 — the empty-response flake on complex multi-turn flows benefits from one more retry. |
|||
| 3d99282897 |
fix(agent): move plan step replacement from reopenSession to setGoal
reopenSession was replacing plan steps on every follow-up message —
including approvals ('go ahead') — which destroyed the plan the operator
just approved, leaving the agent unable to track step progress and looping
run calls until maxIterations.
Fix: setGoal is the explicit signal for 'new sub-task' (the agent calls
it at the start of each follow-up direction). Step replacement now happens
there, not in reopenSession. An approval ('go ahead') does NOT call
set_goal, so the plan stays intact and the agent can execute + complete
it.
|
|||
| a8f04cc9e3 |
fix(agent): open assent window on 'go ahead' after propose_plan
The check len(lastAssistantCalls) == 0 was too restrictive — it only fired when the assistant had ZERO tool calls. But propose_plan + pre-plan research are tool calls, so the assent window never opened when the operator said 'go ahead' after a plan proposal. The agent then tried to execute config_mutation run calls without the assent window, they queued for approval, and the turn deadlocked. Fix: check len(pending) == 0 (no pending APPROVALS) instead of len(lastAssistantCalls) == 0 (no tool calls at all). |
|||
| 487f9ad358 |
fix(agent): reopenSession replaces plan steps for executing sessions too
A follow-up on an executing session (first turn didn't complete_task) is still a new direction — the old plan's steps must not block the new one. Previously reopenSession was a no-op for executing sessions, leaving done steps that caused errPlanInFlight on the next propose_plan call. |
|||
| 3d7fa99560 |
fix(eval): preserve plan generations across iterations
proposePlan: mark pending steps as 'replaced' instead of DELETE, so the generation counter (MAX+1) sees prior generations. Without this, a first plan that was proposed but never executed would be wiped, resetting the counter — a follow-up's plan would look like generation 1 instead of 2. plan-always-readonly: raise max_run_calls from 3 to 6 (agent inspects thoroughly). |
|||
| 844cfe5888 |
fix(agent): read-only plans execute without approval
SOUL.md step 4: all-read-only plans skip the approval wait and execute immediately. Only config_mutation/destructive steps need operator approval. set_goal + propose_plan return text updated to match. Fixes 3/4 eval failures where the agent proposed a plan then waited for approval on a read-only task. |
|||
| 462fb4d77b |
chore(eval): consolidate evals into single evals/ folder
Move golden.yaml from cmd/nomos/eval/evals/ to the root evals/ folder. All manifests now live in one place; the -manifest glob points at evals/*.yaml. |
|||
| e3fa6736c0 |
feat(agent): plan-first gate, iterative follow-ups, reasoning persistence
P1 plan-first: run handler refuses without propose_plan (structural gate,
not SOUL.md prose). Plan window decoupled from set_goal — config_mutation
auto-run only on operator approval (assent window). Closes the approval-free
config_mutation hole confirmed in session d0d562e0.
P2 iteration: reopenSession flips terminal→executing, marks prior plan steps
replaced, clears outcome. proposePlan excludes replaced from in-flight check,
bumps generation. A follow-up on a completed session starts a new sub-task
with a fresh plan — no more errPlanInFlight dead end.
P3 reasoning: accumulate per-iteration text into the persisted row instead
of overwriting with the last text event. Reload shows intermediate thinking,
not just the final summary.
P4 read-only allowlist: add find, tree, locate, systemctl list-timers/
list-unit-files/show, timedatectl, hostnamectl, systemd-analyze, rclone
ls/lsl/md5sum/check/cryptcheck. Fixes the find misclassification from
d0d562e0.
P5 eval harness: new assertion kinds (proposes_plan, plan_before_run,
plan_generations), multi-turn followups, fetch /sessions/{id}/plan. Four
manifests under evals/.
P6 SOUL.md: strip degenerate-case carve-out, add ITERATE step, update
set_goal guidance.
VERSION 0.6.0 → 0.7.0
|
|||
| dd3076a23a |
feat(agent): close all post-fix remainders + golden eval harness (F.1-F.2, C.1-C.2, B.4-B.6, E.1-E.2)
Ships the 9 remaining post-fix items and a golden-conversation eval harness that validates them against the live agent. All 4 evals pass. SOUL.md (F.1, C.2, E.1): - Consolidated three overlapping task-flow sections (MANDATORY TASK FLOW, 'Every chat is a task', 'AFTER EVERY TASK: WRITE BACK') into one. ~50 lines shorter. The operator's 'be more crisp' feedback. - Added anti-patterns: don't re-execute on UI/sidebar complaints (C.2); don't re-run fleet-wide audits when same-day knowledge exists (E.1). - Updated approval vocabulary in step 4 to match tasks.go (approved/yes/ go/proceed/continue/ok/go ahead). Tool-result strings (F.2): - set_goal: tightened to 'Goal set. NEXT: pre-plan (read-only tools only). Then propose_plan. Do not call run.' - update_plan_step: added '(Advance with update_plan_step + run; do not re-propose.)' C.1 — completeTask rejects re-completion of a terminal session: - Returns errTaskAlreadyComplete when status is already done/failed. - The tool result directs: 'Task is already complete. Do not call complete_task again. If the operator pointed out a UI/sidebar inconsistency, fix it with update_plan_step...' B.4 — Surface real model error text: - chatWith's error event now includes finish_reason + refusal text: 'Nomos returned an empty or unusable response (finish_reason=length). Retry or rephrase.' instead of generic 'empty response'. - The resume-failed note already carried errText (B.3), which now has the real context. B.5 — Back off between resume retries (4s, 8s): - resumeSession now sleeps before attempts 1 and 2 (exponential backoff). A transient provider issue gets time to clear instead of 3 identical calls in 3 seconds. B.6 — Don't persist the empty placeholder as a visible bubble: - If a chat turn ends with no text and no tool calls (model empty-response'd and all retries failed), delete the placeholder row instead of persisting an empty bubble. The error was already streamed via done+error=true. E.2 — list_lxcs last-audited hint: - The list_lxcs result now includes last_audited_at — the most recent knowledge entry (tagged audit/update, or titled audit/update) linked via an 'about' edge. The agent can see 'nextcloud — last audited today' and skip re-running it. Tool-call doubling bug fix (found by the eval harness): - main.go + continue.go: the tool_use and tool_result events were both appending separate entries to the persisted tool_calls array, doubling every tool call in the transcript. Confirmed pre-existing (d9cdcee1, v0.3.x era). Fixed: tool_use creates the entry, tool_result merges the result into the same entry (matched by id). One entry per tool call. Golden eval harness (cmd/nomos/eval/): - A standalone Go program that loads YAML manifests of golden conversations + assertions, sends prompts to the chat endpoint, drains the SSE stream (keeping the agent's context alive), and scores structural assertions against the persisted transcript. - 4 golden conversations covering: trivial read-only (degenerate case), plan + proceed (the original duplication bug), UI complaint (no re-exec), fleet audit (knowledge preferred over re-execution). - Structural assertions only (tool-call sequences, plan steps, writeback, completion) — text quality is model-dependent and not scored. - Run: go run ./cmd/nomos/eval -gateway http://localhost:8092 -manifest cmd/nomos/eval/evals/*.yaml (~$0.10/run in OpenRouter credits). Eval results (4/4 passed): trivial_readonly: 2 tool calls, no plan, no run plan_advances_on_proceed: 13 tool calls, propose_plan x1, writes back ui_complaint_no_rerun: 12 tool calls, propose_plan x1, writes back knowledge_preferred_over_rerun: 7 tool calls, search_knowledge x1, 0 run Version 0.5.2 -> 0.5.3 (minor: eval harness + structural hardening). |
|||
| 3de359b85f |
feat(agent): close knowledge loop — refuse complete_task without writeback (D.1+D.2)
D.1 — complete_task structural gate:
- hadDiscovery(ctx, session) reports whether the session ran `run` successfully
against a live target (NOT get_entity/list_lxcs — those are DB lookups, not
new facts). A trivial Q&A that only calls get_entity is a degenerate case
and must NOT be blocked.
- complete_task with outcome=success is REFUSED when hadDiscovery && !
hadEntityWriteback. The refusal fires BEFORE completeTask runs, so the
session stays in 'executing' state and the agent must call
update_entity_attributes/create_relationship then retry complete_task.
An explicit failure/partial is allowed through (the agent is acknowledging
it didn't finish — no reason to force writeback).
- Replaces the prior advisory warning (5.5) which the agent consistently
ignored. The agent saw the warning and ended the task anyway; this gate
makes the writeback a hard prerequisite for success.
D.2 — propose_plan auto-append writeback step:
- When the agent proposes a plan whose steps don't mention
update_entity_attributes or create_relationship, D.2 appends a final
'Write back: update_entity_attributes + create_relationship +
upsert_knowledge' step before persisting. The result string tells the
agent it was appended.
- With the seq-order enforcement (5.6) and D.1's complete_task gate, the
agent must complete the writeback step (and actually call the tools) to
finish. Neither relies on the agent reading SOUL.md.
- Removed the old advisory writeback nudge from propose_plan's result
string — D.2 makes it structural.
- Updated the propose_plan tool description to state both gates crisply.
Verification:
- TestHadDiscoveryAndWriteback: hadDiscovery true only after a successful
`run`; false after failed run, get_entity, or no calls. hadEntityWriteback
true only after update_entity_attributes/create_relationship.
- e2e against the live agent (oikos-nomos-1, v0.5.1):
- D.2: agent proposed 3 steps (no writeback); D.2 auto-appended step 4
'Write back: update_entity_attributes + ...'. Result string said
'(appended a writeback step — your plan didn't include one; step 4)'.
- D.1: agent ran `run` (uptime on lxc:gitea), called complete_task, was
REFUSED ('Refused: this session ran run against live targets (discovery)
but did not call update_entity_attributes...'). Agent self-corrected:
called update_entity_attributes, retried complete_task, succeeded.
Knowledge loop closed end-to-end.
Version 0.5.0 -> 0.5.1 (patch: structural enforcement of existing intent).
|
|||
| 337d577f00 |
fix(agent): refuse plan re-proposal + emit done on error (close divergence chain)
Operator-reported bug: on 'proceed with the rest' the agent re-proposed the
plan, duplicating it in the sidebar. Root cause was a three-bug chain, not
one bug:
1. Trigger — model empty-response on 'proceed' (approval vocabulary didn't
list 'proceed', so the agent wasn't sure it was approved and no-op'd).
2. Amplifier — chatWith emitted 'error' without 'done' on empty response
(agent.go:370). The frontend's onComplete saw !receivedDone and
misclassified the model failure as a network disconnect, calling
handleDisconnect -> resumeSession.
3. Divergence — the reconnect note was generic ('report your state'), so
the agent re-proposed + re-executed instead of advancing the plan.
Fixes (shipped, e2e-validated against the live agent on oikos-nomos-1):
- A.2: proposePlan refuses re-proposal once a step has started (returns
errPlanInFlight). Drops the append-mode safety net (commit
|
|||
| 5caf49bf48 |
mandatory pre-plan flow: goal → research → plan → APPROVE → execute
SOUL.md: mandatory 6-step task flow at TOP of file, unmissable. Agent MUST: set_goal → pre-plan (research only) → propose_plan → STOP and wait for approval → execute (auto-run under plan window). Backend: - set_goal now opens plan window immediately (config_mutation auto-runs) - set_goal result tells agent to do pre-plan + propose_plan, not run - propose_plan result tells agent to STOP and wait for approval - plan window value unified to 'active' (set_goal + propose_plan) This prevents 23 individual approval popups — one plan approval instead. |
|||
| b423cf4dea |
plan-approve-once policy + cooler empty states + remove graph header
Backend: - proposePlan sets plan window in autonomy_settings (nomos:plan:<session>) - run handler checks plan window — auto-executes config_mutation commands within plan without per-action approval - planWindowActive function in server.go - Plan window cleaned up on completeTask (already covered by LIKE '%:' || ) Frontend: - Removed 'Session graph' header bar - Cooler empty states: Plan shows animated dots + 'Awaiting plan…', Activity shows pulsing dots + 'Waiting for activity…' |
|||
| 04677fdf4b |
tool timeline in sidebar + compact chat tools + scroll fixes
- SessionDigest now includes live tool timeline, plan steps, knowledge - ToolCallGroup compact: single-line with collapsible names only (no JSON) - Activity bar moved to bottom of messages, smart scroll respects user position - setGoal now sets status=executing (removed stuck planning state) - PlanProgress merged into SessionDigest, removed from TaskContextPanel - New toolTimeline derived store in chat.ts |
|||
| 60effcb2fe |
session reliability: reconnect, knowledge loop, retire request_execution
Phase 1 — crash recovery: SSE auto-reconnect + backoff, polling gate during disconnect, connection banner with retry button, empty-response retry 3x, non-terminal resume on empty response, persistent error cards. Phase 2/4 — visibility + continuation: custom ExecutionStatus renderer, approvals extracted on every tool_result (not just done), activity bar with status/goal, SessionDigest live polling, Continue button. Phase 3 — cleanup: complete_task auto-cancels orphaned approvals, deletes assent/destructive window keys, propose_plan marks pending steps as replaced, plan step seq-order enforcement. Phase 5 — knowledge loop: list_lxcs state filter (active/destroyed), SOUL.md unmissable writeback section, propose_plan validation nudge, complete_task writeback check, upsert_knowledge about array support, plan generation grouping in frontend, session approval count badge. Retire request_execution — all mutations now route through run. Updated SOUL.md, AGENTS.md, CLIENTS.md, skills, and agent system notes. Migration 020: plan step generation column, audit_log session_id index, nomos_plan_executions pending-approval index. |
|||
| 0c0f35a3a9 |
feat(web): split SPA from oikos binary, require auth on every route
Phase 0 of plans/2026-07-12-wails-desktop-app.md. The control-room SPA is no longer embedded (web/embed.go deleted); it's a standalone static build served separately (make ui / make deploy-ui). The api process adds CORS and drops the dev-open auth bypass — every route now needs a real bearer token, including SSE (?token= query param, EventSource can't set headers) and api's own /agent proxy to nomos (previously unauthenticated by omission). nomos was an unauthenticated client of api's /mcp and approval-decision endpoints; closing dev-open would have broken it, so it now sends Authorization: Bearer $OIKOS_MCP_BEARER_TOKEN on every call back to api. SPA gets a runtime config module (config.ts) and a Config.svelte first-launch/reconfigure page, reachable afterwards via a "Connection" entry in the sidebar footer. Every fetch() in api.ts routes through fetchWithAuth so the same build works same-origin (browser prod, Vite dev proxy) or cross-origin (future Wails webview, remote access). Six gaps found against the plan and the live Caddy topology while implementing — documented in the plan's "Plan review" section, most notably: api's own /agent mount was never behind combinedAuth (fixed), and production's Authentik forward-auth needs a bearer-token bypass for API routes that this repo's Caddyfile.oikos reference copy now has, but the real dtoro/caddy-conf deploy does not yet. Verified live: cross-origin static SPA + API, CORS, bearer auth, SSE query-token auth, and localStorage persistence all confirmed working in-browser. Full Go test suite and npm run build pass with no regressions against the pre-change baseline. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> |
|||
| de126daf43 |
feat(web): fold Events/Agent/Audit into EntityDetail; tag agent_activity with entity_id
Events, Agent, and Audit were standalone read-only pages that never cross-referenced the entity they related to. Fold them into EntityDetail as entity-scoped cards (Agent activity, Audit trail) alongside the existing Signals/Executions/Knowledge cards, and give the Signals card real Ack/Mute/Resolve actions. Signals stays a standalone page since it's the only one with cross-entity triage value (badge count, actions). Also fixes the underlying reason those new cards would've stayed empty: agent_activity rows were never tagged with entity_id at insert time (cmd/nomos/store.go, internal/mcp/server.go), even though the column and the API filter both support it. Added a best-effort resolver that checks common tool-arg keys (target, entity_slug, slug, ...) against the entities table. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> |
|||
| 3b9c75fa3f |
fix(agent): task completion safety net — stop tasks sticking at Running
Implements fixes 1-3 of plans/2026-07-11-task-completion-safety-net.md. Confirmed live that 50/50 production sessions never reached a terminal status because the model almost never calls complete_task, even for trivial single-tool Q&A turns SOUL.md explicitly calls out as needing it. - Inline safety net (agent.go): a session that never called set_goal never framed itself as a structured task, so its first plain-text turn-end IS the task ending — auto-complete it there instead of leaving status stuck at its creation default forever. - Idle sweep (continue.go, new completion_nudges column): goal-bearing sessions that stall get one nudge, then auto-close with outcome=partial if the nudge goes unanswered, mirroring the pattern resumeSession already uses for a different stuck-session failure mode. Fix 4 (backfill of the 50 already-stuck live sessions) is deliberately separate — deferred until this is deployed and verified live, per the plan's implementation order. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> |
|||
| 11c18e8956 |
perf(agent): cache the MCP tool list per client (F1)
Fix F1 of plans/2026-07-11-nomos-agent-code-review.md, the last item. buildTools called listToolsFull (a tools/list MCP round-trip) at the start of EVERY chat turn, including every auto-continuation resume — the tool list is static for the lifetime of one MCP connection, changing only when the api process re-registers tools (a restart, which this client already detects and reacts to via reconnectLocked). Re-fetching it every single turn was avoidable network+parsing work on the hot path. mcpClient now caches the parsed tool list after its first fetch, guarded by its own mutex (kept separate from the request-serializing mu so a cache check never contends with an in-flight doRequest call). reconnectLocked clears the cache — an api restart may have changed what's registered, so a stale cache would be wrong, not just slow. fleetSnapshot's get_health_summary call is deliberately left uncached — it's meant to be "as of now." Since each session gets its own client (the per-session pool from the concurrency work), this caches per-task-conversation rather than globally: a task's FIRST turn still pays the round-trip, every turn after reuses the cached list — which is exactly the case that mattered (long-running, heavily-autonomous tasks with many auto-continuation resumes). Verified live via the api's request log: a brand-new session's first turn made 3 MCP calls (initialize, tools/list, get_health_summary); a second turn on the SAME session made exactly 1 (only get_health_summary) — tools/list correctly skipped. This completes the implementation order in plans/2026-07-11-nomos-agent-code-review.md — every A/B/D/E/F finding from the review (excluding C1, explicitly deferred per operator instruction) is now fixed, tested, and verified live. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> |
|||
| 6d4f6de676 |
fix(agent): mark a task failed when its resume permanently gives up (B3)
Fix B3 of plans/2026-07-11-nomos-agent-code-review.md. resumeSession's retry loop (used by both auto-continuation and panel-answered questions) already retried once on a transient LLM failure, but if BOTH attempts came back empty/erroring, the code just logged and returned — the task was left at whatever status it already had (typically 'executing' or 'awaiting_input') with no outcome, no operator-visible signal beyond an inert error line buried in the transcript, and no way to tell a genuinely stuck task apart from one quietly still working. On permanent failure, now calls store.completeTask(outcome='failure', a summary built from the error) so the task board reflects reality instead of showing a task that looks perpetually in-progress. Uses context.Background() for that write, matching resumeSession's own persistence pattern, since the context that led to the failure may itself be in a bad state. This doesn't prevent the operator from continuing to work the task via a fresh chat message afterward — it only replaces silent hanging with a real status. A full live induction of a permanent LLM outage would require breaking the model/API-key config for the whole nomos container — too invasive for this fix's priority. Verified instead that the new branch stays correctly dormant on the happy path: ran a real ask_operator → panel-answer → resume cycle end-to-end and confirmed the task landed at status='executing' with no outcome set, proving the failure-handling code doesn't false-positive on a normal successful resume. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> |
|||
| c3901641d1 |
fix(agent): bound conversation history replayed to the LLM (A2)
Fix A2 of plans/2026-07-11-nomos-agent-code-review.md. chatWith replayed a
session's ENTIRE message history into the LLM's context on EVERY turn, no
windowing, no token budget — confirmed against a documented production case
(a single turn with 70 tool calls, messages up to 106KB). Every subsequent
turn of a long-running or heavily-autonomous task re-sent that ever-growing
history in full — a real cost/latency/eventual-context-limit risk for
exactly the tasks this system runs longest (many auto-continuation cycles).
Design call (flagged in the review as needing one before implementation):
a fixed-size window for LLM replay specifically, not the UI's own transcript
view. Simplest option that still keeps roughly the current task's working
context; a token-aware trim or LLM-summarize-on-drop are documented as
stretch options if 30 proves insufficient in practice.
- store.go: new getRecentMessages(ctx, sessionID, limit) — last `limit`
messages in chronological order, plus whether older ones were omitted.
getMessages (used by the UI's GET /sessions/{id}) is untouched and stays
unbounded — the operator should still see a task's full history regardless
of length; only what gets sent to the model is bounded.
- agent.go: chatWith uses getRecentMessages(sessionID, historyWindowSize=30)
instead of the unbounded getMessages. When truncated, injects a system
note telling the model explicitly that older turns exist but aren't shown,
so it checks upsert_knowledge/search_knowledge rather than assuming
something wasn't done just because it isn't visible.
New cmd/nomos/store_test.go: real Postgres integration tests (mirroring
internal/db/integration_test.go's throwaway-database pattern, guarded by
OIKOS_TEST_DATABASE_URL). TestGetRecentMessages_Truncation is the direct
proof for this fix (35 messages → 30 returned, correctly ordered,
truncated=true; 5 messages → all 5, truncated=false) — both cases run
against a fully-migrated database, not mocked. Also added
TestProposePlan_AppendVsReplace, closing part of the review's test-coverage
finding (E) by permanently regression-testing the earlier append-vs-replace
plan fix (commit
|
|||
| 76f76308cc |
fix(agent): D1-D3 cleanups — dead code, N+1 query, unvalidated outcome enum
Fixes D1-D3 of plans/2026-07-11-nomos-agent-code-review.md: - D1: deleted isTaskTool — defined, never called (dispatch already checks handleTaskTool's own `handled` return value). - D2: recordTouched issued one SELECT per entity slug found in a tool call's args; batched into one `WHERE slug = ANY($1)` query. Verified live: a turn naming three separate entities recorded involves edges for all three via the single batched lookup. - D3: complete_task's outcome had a declared enum (success|failure|partial) in its tool schema but nothing validated it — an out-of-enum value (model typo or a weaker model not respecting the schema) silently persisted as-is, with only "failure" special-cased (anything else became status='done' regardless of what the value actually said). Now validated in handleTaskTool: empty defaults to "success" (unchanged), a recognized value passes through, anything else defaults to "partial" (safer than silently treating an unrecognized value as success) with a warning logged. Verified live: instructed the agent to call complete_task with outcome="unclear" — persisted as outcome='partial', not the literal invalid string. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> |
|||
| 926969a03f |
fix(agent): live chat turns persist incrementally, survive client disconnect
Fix A3 of plans/2026-07-11-nomos-agent-code-review.md. handleChat only ever saved the assistant message ONCE, after a.chat(...) returned, using ctx := r.Context() for that write — the same context that cancels the instant the client disconnects (Stop button, tab close, network blip). A disconnect mid-turn meant the final save ran with an already-cancelled context and its error was never checked: the entire turn's tool-call history was silently lost from the persisted transcript, even though real work (executions launched, knowledge written) had already happened server-side. Brought handleChat in line with resumeSession's existing pattern (continue.go): insert a placeholder assistant row immediately, update the SAME row after every tool call. The key fix is WHICH context the writes use — a new pctx := context.Background() for every DB write in this handler (session creation/touch, the user message, question auto-close, the placeholder + incremental updates, the title update), while ctx/r.Context() still gates the agent's own work (a.chat) and the SSE writes exactly as before — a disconnect still correctly stops the agent from doing further work, it just no longer also erases what it already did. Verified live: sent a message requiring 6 tool calls (get_entity/ get_relations/get_blast_radius on two targets) and force-killed the client connection mid-stream with curl -m 12 (confirmed via exit code 28). Before this fix the persisted transcript would show 0 tool-call entries; after, all 12 raw tool_use/tool_result entries (6 calls × 2) were present and correctly attributed by tool name — proving both that progress survives an abort and that the incremental writes aren't corrupting the data. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> |
|||
| c5ffaec85b |
fix(agent): panic recovery on every background goroutine (B1+B2)
Fixes B1 and B2 of plans/2026-07-11-nomos-agent-code-review.md together, since the right granularity for B1 in the auto-continuation worker turned out to require B2's restructuring anyway (see below). B1: grep -rn "recover()" cmd/nomos/ internal/mcp/ internal/httpapi/ returned nothing before this — every explicitly-spawned goroutine (continuation worker, resumed chat turns, async execution dispatch, the SSE listener, two duplicate sshExec implementations' output-collector goroutines) crashed the whole process on an unhandled panic, not just that one goroutine. More consequential post-concurrency: more simultaneous unattended background work means more surface area for one bad input to end every running task. New internal/safego package: Go(label, fn) launches fn in a goroutine with a recover-and-log wrapper. Applied at every bare `go` spawn site across the three packages. Two sites needed bespoke handling instead of the generic helper because their callers block on a channel and a silent recover would just make them hang until timeout: sshExec's output-collector goroutine (two near-identical copies, internal/mcp/server.go and internal/httpapi/phase3.go) and httpapi's ListenAndServe goroutine — both now recover AND send a synthetic error result so the waiting select unblocks immediately instead of waiting out the full timeout. httpapi's sseListener got extra treatment: its per-notification handling was extracted into handleNotification with its own recover, so a panic decoding ONE malformed pg_notify payload can't kill the listener goroutine for every connected SSE client — the outer goroutine spawn only needs to guard the connection setup/reconnect code around it. B2: cmd/nomos/continue.go's processContinuations used to run every pending continuation SEQUENTIALLY in a plain for loop, in the SAME goroutine as the ticker — meaning (a) task B's continuation waited for task A's full (up to 10-minute) resumed turn to finish first, undercutting this session's earlier concurrency work on exactly the path autonomous tasks depend on most, and (b) an unrecovered panic anywhere in that call chain didn't just crash the process (B1) — even WITH B1's recovery wrapped only at the top-level worker spawn, the panic would still unwind the ENTIRE ticker-loop goroutine, silently ending auto-continuation for every task until nomos restarted. Fixed by spawning each pending item via safego.Go individually: real parallelism, and a bad item can now only ever take down its own goroutine. Added internal/safego/safego_test.go: TestGo_RecoversPanic is the concrete proof — a deliberate panic inside Go() that would otherwise crash the whole test binary; reaching the assertion after it IS the evidence recovery works. Verified live against the rebuilt containers: full chat turn round-tripped correctly (hostname lookup, 2 iterations, normal completion) — no regression from threading safego.Go through the tool-dispatch/continuation paths. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> |
|||
| 3919ec37d7 |
fix(agent): word-boundary matching + contracted negatives in chat-assent
Fix A1 of plans/2026-07-11-nomos-agent-code-review.md. isAssent and
isTypedConfirmation used a space-padded word-boundary check for negation
words but a bare strings.Contains for assent/confirm words — confirmed live
via test probes: isAssent("...maybe yesterday's logs...") returned true
("yes" matched inside "yesterday"), and isTypedConfirmation("I haven't
confirmed anything yet") returned true ("confirm" matched inside "confirmed",
and "haven't" wasn't in negationWords — only "don't"/"do not" were).
isTypedConfirmation is the sole gate for DESTRUCTIVE actions, so the second
case meant a message merely stating something hadn't been confirmed could
read as an explicit confirmation.
- Replaced the ad-hoc space-padding/prefix-check negation logic with proper
tokenization (wordTokenRe) + containsPhrase, matching WHOLE tokens/phrases
only — never a mid-word substring. Handles curly apostrophes too (a
pre-existing gap: the old straight-quote-only check would have missed
"don't" typed with a smart quote).
- Added contracted negatives (haven't, hasn't, isn't, wasn't, aren't, can't,
cannot, won't, wouldn't, shouldn't, didn't, doesn't) to negationWords.
Deliberately did NOT add a bare "not" — too broad, would false-negative
ordinary assent like "go ahead, this is not risky".
- Added regression tests for both confirmed cases plus a couple of adjacent
ones (eyesight/isn't, can't confirm) so a future change can't silently
reintroduce either bug.
All existing assent/confirmation tests pass unchanged — this is a pure
robustness fix, not a behavior change for any previously-correct case.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
|||
| a4ea542f3e |
fix(concurrency): per-session MCP client pool — removes cross-task tool-call blocking
Fix 3 of plans/2026-07-11-concurrent-task-execution.md, the throughput one. nomos held exactly one *mcpClient for the whole process, shared by every /chat goroutine. Its mutex was held for the full duration of each tool round-trip, and `run` executes its SSH command SYNCHRONOUSLY inside that round-trip (capped at up to 10 minutes) — so while Task A was mid-`run`, every other task's tool calls, even a trivial get_entity, queued behind that single lock. Tasks could think (LLM calls) in parallel but never act in parallel. The MCP server has no per-connection state to protect (newServer returns one shared *mcp.Server instance whose handlers close only over the DB connection pool, already safe for concurrent use) — the mutex existed purely because the client reused one stateful transport session. So the fix doesn't touch the server at all: - New mcpClientPool (cmd/nomos/main.go): one *mcpClient per session id, created lazily (a real MCP initialize handshake) on first use and cached; session-less traffic (the ephemeral no-DB-store path, the structured /query endpoint) gets its own fixed, reused key instead of a fresh connection per request. Idle clients (20 min past last use — long enough to outlive a single slow `run`) are evicted on a 5-minute sweep ticker. - agent.go: `client *mcpClient` → `clients *mcpClientPool`; every call site (buildTools, fleetSnapshot, the tool-dispatch loop) now resolves its own session's client via clients.get(sessionID) instead of reaching for one shared field. A task's own tool calls stay sequential (already true — the agent loop calls tools one at a time within a turn) but no longer block anyone else's. - main.go: handleQuery takes the pool instead of a client (keyed "query", a fixed non-session slot); shutdown calls pool.closeAll(). Verified live against the deployed stack: fired a slow-but-ungated command (`ping -c 15 127.0.0.1`, read-only per policy's allowlist, no approval needed) as Task A, then — 2s into A's run — a trivial hostname lookup as Task B, both through the real /chat endpoint. Task A's ping genuinely ran ~14.3s (confirmed via its own execution record and the agent's reported output). Task B returned in 6s total, well before A finished — proving it was never queued behind A's connection. Before this fix, B would have been forced to wait out A's entire ~14.3s hold on the single shared client. This completes plans/2026-07-11-concurrent-task-execution.md's required scope — only the explicitly optional/deferred Fix 4 (a concurrency/cost cap, pending real usage data) remains. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> |
|||
| 9ef1ba3702 |
fix(concurrency): scope assent/destructive windows to session, not just agent
Fix 1 of plans/2026-07-11-concurrent-task-execution.md — the safety-critical
one. The assent window (and destructive window) were keyed purely by agent
id ("assent_window.agent:<uuid>"). With one agent:nomos entity serving every
concurrent task, this meant approving Task A's plan opened a window that ANY
concurrently-running task's config-mutation/destructive actions could also
ride, auto-executing without their own approval.
- store.go / agent.go: assentWindowActive/openAssentWindow and
destructiveWindowActive/openDestructiveWindow/destructiveWindowKey all gain
a sessionID parameter; keys become
"assent_window.agent:<id>.session:<sessionID>" and
"destructive_window.agent:<id>.target:<slug>.session:<sessionID>". Missing
session id fails closed (no window) rather than falling back to the old
agent-wide key.
- continue.go: the auto-continuation worker's window check moved from once-
per-batch to once-per-pending-item, scoped to that item's own session —
it was previously checking ONE agent-wide window for a batch that can span
multiple tasks.
- agent.go tool-dispatch: injects `_session_id` into a COPY of the wire args
sent to the MCP server (never into the args used for the emitted/logged/
persisted tool call, and never part of any tool's declared InputSchema —
invisible to the model) so the gating checks on the OTHER side of the
process boundary know which task is asking.
- internal/mcp/server.go: assentWindowActive/destructiveWindowActive/
classifyAndGate gain the same sessionID parameter, read from
args["_session_id"] at the three call sites (request_execution's
apt_upgrade/pct_create branches, and the shared classifyAndGate used by
restart/pct_exec/systemctl/run).
Verified against the live stack with the exact scenario from the plan: opened
an assent window for session A only, then called `run` with an identical
config-mutation command for session A (window open) and session B (same
agent, no window). A auto-ran (execution status completed); B correctly
queued for approval (pending_approval) instead of bleeding through — proven
at both the MCP response text and the executions table.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
|||
| e30813a43d |
feat(tasks): make research-first / knowledge-write-back-last explicit steps
Closes the gap that made the knowledge loop optional/implicit: every non-trivial task now has an EXPLICIT first plan step (research) and last plan step (write back), not just background behavior the model might skip. New MCP tools (the agent had no way to do these before — only REST endpoints existed, unexposed to it): - update_entity_attributes(slug, attributes): shallow-merge new/changed facts into an entity (an IP, a version, a discovered port) so a future task doesn't have to rediscover them from scratch. No approval required — this updates the knowledge graph, not live infra. - create_relationship(source, target, type): record a discovered edge (depends-on, hosts, provides, ...). Idempotent, FK-validated against the ontology's relationship_types, no approval required. SOUL.md: restructured the task loop so step 1 is explicitly "gather knowledge, not just status" (get_entity_knowledge, search_knowledge, get_relations, get_blast_radius, http_get) and the last step before complete_task is explicitly "write back" (update_entity_attributes, create_relationship, upsert_knowledge) — both called out as real plan entries the operator should see in propose_plan, not silent side-work. This is what prevents the graph drifting from reality and is the concrete mechanism behind "tasks compound." propose_plan's tool description reinforces the same first-step/last-step convention at the call site. Verified against the live stack: both tools registered and callable via MCP; update_entity_attributes merged an attribute correctly; create_relationship rejected an invalid type (FK violation, clear error) and succeeded with a valid type+direction, confirmed idempotent (2 calls, 1 row). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> |
|||
| 5384499903 |
fix(tasks): plan panel showed only the latest step, not the full plan
Root cause: proposePlan unconditionally deleted and replaced the whole
session_plan_steps list on every call. The model isn't strictly held to
"call propose_plan once with the full list" — nothing stopped it (and
production evidence + live testing showed it happening) from calling
propose_plan once per step as it worked. Each such call wiped every
already-completed step, so the operator only ever saw the model's latest
single step ("1/1") instead of the real, growing plan.
Fix, two layers:
- store.go: proposePlan now only does a destructive replace when no step
has left 'pending' yet (a genuine pre-execution revision). Once any step
has started, a new call APPENDS after the current max seq instead of
wiping — so the panel accumulates the full history regardless of how the
model chooses to call the tool. plan.proposed now carries `appended` so
the frontend knows whether to replace or append.
- workspace.ts: plan.proposed handler respects `appended` (update vs set).
- tasks.go / SOUL.md: strengthened the propose_plan description and task-
loop guidance to call it ONCE with the complete step list end-to-end,
using update_plan_step (not re-calling propose_plan) to advance — fixing
the root behavioral cause, with the store-side append as a safety net
that holds even if the model still calls it incrementally.
Verified: forced the exact incremental-call pattern (propose_plan with 1
step, mark it running, propose_plan again with 1 more step) — the second
call appended at seq 2 instead of erasing seq 1, and its plan.proposed
event carried appended=true.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
|||
| 991e7d0900 |
feat(tasks): phase 6 — live TaskContextPanel (goal, plan, question, entities)
Replaces the chat right rail's ad-hoc Digest+Graph stack with a single
TaskContextPanel that renders the task's live working state, driven by the
always-on events stream (not the per-turn chat SSE) so it keeps updating
during server-side auto-continuation/resume:
- GoalHeader: goal + status pill (planning/executing/awaiting_input/done/
failed), sourced from the sessions list.
- PlanProgress: ordered steps with live status icons + progress bar, hydrated
via new GET /sessions/{id}/plan; clicking a step with a target opens its
EntitySheet (no fake "jump to transcript" — bits-ui Collapsible content
isn't force-mounted, so a DOM-scroll jump would silently no-op for
collapsed tool groups).
- OperatorQuestion: the pinned structured question card (prompt/why/entity
chips/option buttons/free-text), hydrated via new GET /sessions/{id}/
questions; answering POSTs to the existing answer endpoint.
- SessionGraph upgraded to a live entity panel: entity.touched pulses the
node (animated ring) and shows "Now touching <slug>"; health.changed shows
a transient diff badge for touched entities.
- SessionDigest gains a success/failure/partial outcome banner and now also
refetches when the task's status changes, not just on session switch.
Two bugs found and fixed while wiring this up:
- workspace.ts's status-refresh trigger only covered goal.set/task.status;
question.raised/answered didn't refresh the sessions list, so GoalHeader's
pill went stale after answering via the panel (resumeSession runs entirely
server-side — no client 'done' event to piggyback a refresh on). Now every
status-affecting event triggers the (debounced) refetch.
- Forgot to rebuild the nomos container after adding the /plan and
/questions endpoints, so they silently fell through to the old default GET
handler — caught via a live curl diff against the running container,
not a code read.
Verified end-to-end against the live stack: goal/plan/question all update
without a reload as the agent works; answering a question via the panel
resumes the agent and the header pill correctly flips to Executing;
entity.touched pulses the live graph.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
