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column to session_plan_steps (migration 030) - track WHY steps are replaced (wrong_diagnosis/scope_change/superseded/etc) - force fresh propose_plan on session resume (reopenSession marks old plan) P2 — cognitive guardrails: - SOUL.md scope-gate rule: ask before chasing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)
2026-08-04 23:15:47 +02:00
parent 1aaedf498a
commit c3f478b8f8
10 changed files with 773 additions and 42 deletions
--- a/cmd/nomos/agent.go
+++ b/cmd/nomos/agent.go
@@ -382,7 +382,12 @@ func (a *agent) chatWith(ctx context.Context, sessionID, message, systemInject s
 		var msg openai.ChatCompletionMessage
 		var acc openai.ChatCompletionAccumulator

-		for attempt := 0; attempt <= maxLLMRetries; attempt++ {
+		// Capture token usage from this LLM response for activity logging.
+	// Previously always NULL — every agent_activity row had no token
+	// count. Now each tool call in this iteration gets the same total.
+	totalTokens := 0
+
+	for attempt := 0; attempt <= maxLLMRetries; attempt++ {
 			acc = openai.ChatCompletionAccumulator{}
 			stream := a.provider.Chat.Completions.NewStreaming(ctx, params, a.reqOpts...)
 			for stream.Next() {
@@ -414,14 +419,19 @@ func (a *agent) chatWith(ctx context.Context, sessionID, message, systemInject s
 			msg = acc.Choices[0].Message
 			finishReason := acc.Choices[0].FinishReason

+			// Capture token usage from this iteration.
+			if acc.Usage.TotalTokens > 0 {
+				totalTokens = int(acc.Usage.TotalTokens)
+			}
+
 			if len(msg.ToolCalls) == 0 {
 				if isRefusalOrEmpty(msg.Content) {
-					if attempt < maxLLMRetries {
-						slog.Warn("nomos: empty or refusal response, retrying",
-							"session", sessionID, "iter", i+1, "attempt", attempt+1,
-							"content_len", len(msg.Content), "finish_reason", finishReason)
-						continue
-					}
+				if attempt < maxLLMRetries {
+					slog.Warn("nomos: empty or refusal response, retrying",
+						"session", sessionID, "iter", i+1, "attempt", attempt+1,
+						"content_len", len(msg.Content), "finish_reason", finishReason)
+					continue
+				}
 					// B.4: surface the real error context (finish_reason +
 					// refusal text) instead of a generic "empty response" —
 					// the operator can tell "content_filter — rephrase" from
@@ -505,7 +515,7 @@ func (a *agent) chatWith(ctx context.Context, sessionID, message, systemInject s
 					slog.Warn("nomos: run retry cap hit — refusing dispatch",
 						"target", t, "failures", n, "session", sessionID)
 					a.store.logActivity(ctx, a.agentID, sessionID, tc.Function.Name, args,
-						tc.Function.Arguments, directive, 0, false, correlationID)
+						tc.Function.Arguments, directive, 0, false, correlationID, totalTokens)
 					emit(agentEvent{
 						Type:      "tool_result",
 						Data:      map[string]any{"name": tc.Function.Name, "result": directive, "id": tc.ID, "retry_capped": true},
@@ -556,7 +566,7 @@ func (a *agent) chatWith(ctx context.Context, sessionID, message, systemInject s
 			inputStr := string(inputJSON)

 			if callErr != nil {
-				a.store.logActivity(ctx, a.agentID, sessionID, tc.Function.Name, args, inputStr, callErr.Error(), elapsed, false, correlationID)
+				a.store.logActivity(ctx, a.agentID, sessionID, tc.Function.Name, args, inputStr, callErr.Error(), elapsed, false, correlationID, totalTokens)

 				// Retry cap: dispatch errors (e.g. MCP client timeout)
 				// count toward the cap too. A command that keeps timing
@@ -586,7 +596,7 @@ func (a *agent) chatWith(ctx context.Context, sessionID, message, systemInject s
 			}

 			resultJSON, _ := json.Marshal(result)
-			a.store.logActivity(ctx, a.agentID, sessionID, tc.Function.Name, args, inputStr, string(resultJSON), elapsed, true, correlationID)
+			a.store.logActivity(ctx, a.agentID, sessionID, tc.Function.Name, args, inputStr, string(resultJSON), elapsed, true, correlationID, totalTokens)

 			// Link any execution this tool queued/started back to this
 			// session, so the auto-continuation worker can feed its result
--- a/cmd/nomos/main.go
+++ b/cmd/nomos/main.go
@@ -818,7 +818,7 @@ func newMCPClient(baseURL, token string) (*mcpClient, error) {
 	c := &mcpClient{
 		baseURL: baseURL,
 		token:   token,
-		http:    &http.Client{Timeout: 30 * time.Second},
+		http:    &http.Client{Timeout: 120 * time.Second},
 	}

 	resp, err := c.doRequest("initialize", map[string]any{
--- a/cmd/nomos/store.go
+++ b/cmd/nomos/store.go
@@ -807,10 +807,11 @@ func (s *store) setGoal(ctx context.Context, sessionID, goal string) error {
 	// Replace any prior plan steps (done/running/pending/...) as `replaced`.
 	// The rows are kept for the generation counter + audit trail; proposePlan
 	// excludes `replaced` from its in-flight check, so the next propose_plan
-	// takes the fresh-generation path.
+	// takes the fresh-generation path. replaced_reason records the cause
+	// (2026-08-04 plan-step integrity audit).
 	s.pool.Exec(ctx,
-		`UPDATE session_plan_steps SET status = 'replaced', finished_at = COALESCE(finished_at, now()) WHERE session_id = $1 AND status <> 'replaced'`,
-		sessionID)
+		`UPDATE session_plan_steps SET status = 'replaced', replaced_reason = $2, finished_at = COALESCE(finished_at, now()) WHERE session_id = $1 AND status <> 'replaced'`,
+		sessionID, "goal superseded")
 	if _, err := s.pool.Exec(ctx,
 		`UPDATE agent_sessions SET goal = $2, status = 'executing', title = $2, last_active_at = now() WHERE id = $1`,
 		sessionID, goal); err != nil {
@@ -850,6 +851,14 @@ func (s *store) reopenSession(ctx context.Context, sessionID string) bool {
 	s.pool.Exec(ctx,
 		`UPDATE agent_sessions SET status = 'executing', outcome = NULL, summary = NULL, last_active_at = now() WHERE id = $1`,
 		sessionID)
+	// Mark the prior plan's steps as replaced so the P1 plan-first gate in
+	// classifyAndGate forces a fresh propose_plan before any run. Without
+	// this, the agent could resume a session and call run against the old
+	// (completed) plan — exactly what caused the ZimaOS continuation to
+	// have 81 ad-hoc tool calls with zero plan structure (2026-08-04).
+	s.pool.Exec(ctx,
+		`UPDATE session_plan_steps SET status = 'replaced', replaced_reason = $2, finished_at = COALESCE(finished_at, now()) WHERE session_id = $1 AND status <> 'replaced'`,
+		sessionID, "session reopened — awaiting new plan")
 	_ = observability.Event(ctx, sqlcgen.New(s.pool), "task.reopened", s.taskEntityPtr(ctx, sessionID),
 		"info", "nomos", sessionID, map[string]any{"prior_status": currentStatus})
 	return true
@@ -908,9 +917,11 @@ func (s *store) proposePlan(ctx context.Context, sessionID string, steps []planS
 	// The rows are kept for the generation counter (MAX(generation)+1 below)
 	// and the plan_generations eval assertion. `replaced` steps are excluded
 	// from the anyStarted check above, so they don't block this proposal.
+	// replaced_reason records the cause — required by the plan-step integrity
+	// gate (2026-08-04 session audit).
 	if _, err := tx.Exec(ctx,
-		`UPDATE session_plan_steps SET status = 'replaced', finished_at = COALESCE(finished_at, now()) WHERE session_id = $1 AND status = 'pending'`,
-		sessionID); err != nil {
+		`UPDATE session_plan_steps SET status = 'replaced', replaced_reason = $2, finished_at = COALESCE(finished_at, now()) WHERE session_id = $1 AND status = 'pending'`,
+		sessionID, "superseded by new plan generation"); err != nil {
 		return nil, err
 	}

@@ -972,7 +983,7 @@ func (s *store) proposePlan(ctx context.Context, sessionID string, steps []planS
 // be marked complete while an earlier step is still pending, preventing the
 // agent from marking step 5 done before step 4 (observed in production: the
 // agent rushed to close all steps in a final turn, in reverse order).
-func (s *store) updatePlanStep(ctx context.Context, sessionID string, seq int, status, execID string) error {
+func (s *store) updatePlanStep(ctx context.Context, sessionID string, seq int, status, execID, replacedReason string) error {
 	if s == nil || sessionID == "" || sessionID == "ephemeral" {
 		return nil
 	}
@@ -1025,16 +1036,30 @@ func (s *store) updatePlanStep(ctx context.Context, sessionID string, seq int, s
 	// status <> 'replaced' is defense-in-depth: MAX(generation) can't hold a
 	// replaced row, but if it ever could, this refuses the write instead of
 	// resurrecting it. No matching row → errPlanStepNotFound (stale/out-of-range seq).
-	err := s.pool.QueryRow(ctx, `
-		UPDATE session_plan_steps
-		SET status = $4, execution_id = COALESCE($5, execution_id)`+stamp+`
-		WHERE session_id = $1 AND generation = $2 AND seq = $3 AND status <> 'replaced'
-		RETURNING id, target_slug`, sessionID, curGen, seq, status, execPtr).Scan(&stepID, &targetSlug)
-	if err != nil {
-		if errors.Is(err, pgx.ErrNoRows) {
-			return errPlanStepNotFound
+	if status == "replaced" && replacedReason != "" {
+		err := s.pool.QueryRow(ctx, `
+			UPDATE session_plan_steps
+			SET status = $4, execution_id = COALESCE($5, execution_id), replaced_reason = $6`+stamp+`
+			WHERE session_id = $1 AND generation = $2 AND seq = $3 AND status <> 'replaced'
+			RETURNING id, target_slug`, sessionID, curGen, seq, status, execPtr, replacedReason).Scan(&stepID, &targetSlug)
+		if err != nil {
+			if errors.Is(err, pgx.ErrNoRows) {
+				return errPlanStepNotFound
+			}
+			return err
+		}
+	} else {
+		err := s.pool.QueryRow(ctx, `
+			UPDATE session_plan_steps
+			SET status = $4, execution_id = COALESCE($5, execution_id)`+stamp+`
+			WHERE session_id = $1 AND generation = $2 AND seq = $3 AND status <> 'replaced'
+			RETURNING id, target_slug`, sessionID, curGen, seq, status, execPtr).Scan(&stepID, &targetSlug)
+		if err != nil {
+			if errors.Is(err, pgx.ErrNoRows) {
+				return errPlanStepNotFound
+			}
+			return err
 		}
-		return err
 	}
 	// Anchor the event to the step's target entity when it has one, else the task.
 	entPtr := s.taskEntityPtr(ctx, sessionID)
@@ -1218,9 +1243,141 @@ func (s *store) completeTask(ctx context.Context, sessionID, outcome, summary st
 	_ = observability.Event(ctx, sqlcgen.New(s.pool), "task.status", entPtr, severity, "nomos", sessionID,
 		map[string]any{"status": status, "outcome": outcome, "summary": summary,
 			"cancelled_executions": cancelledCount, "blocker": blocker})
+	// Auto-persist knowledge so the graph learns from this session regardless
+	// of whether the agent remembered to call upsert_knowledge (2026-08-04
+	// session audit: only 2.4% of sessions called upsert_knowledge manually).
+	if outcome == "success" || outcome == "partial" {
+		autoUpsertKnowledge(ctx, s, sessionID, outcome, summary)
+	}
+	// Plan quality metric: compute step completion rate for the session's
+	// current plan generation. Tracked as a task attribute so the trend
+	// can be monitored over time (2026-08-04 session audit: 38% baseline).
+	writePlanCompletionRate(ctx, s, sessionID)
+	// Auto-feedback: create a feedback entry linking the session's outcome
+	// to its last execution, feeding the pattern-extraction pipeline that
+	// has been empty since launch (2026-08-04 session audit: 0 feedback rows).
+	if outcome == "success" || outcome == "partial" {
+		autoFeedback(ctx, s, sessionID, outcome, summary)
+	}
 	return nil
 }

+// autoUpsertKnowledge creates a knowledge entry for a completed session,
+// capturing what was done and linking it to the entities involved. Called
+// automatically from completeTask so every session leaves a trace, even if
+// the agent forgot to call upsert_knowledge. Only fired for success/partial
+// outcomes (failures don't have actionable discoveries).
+func autoUpsertKnowledge(ctx context.Context, s *store, sessionID, outcome, summary string) {
+	var goal string
+	if err := s.pool.QueryRow(ctx,
+		`SELECT COALESCE(goal, '') FROM agent_sessions WHERE id = $1`,
+		sessionID).Scan(&goal); err != nil || goal == "" {
+		return
+	}
+	title := "Session " + sessionID[:8] + ": " + goal
+	if len(title) > 200 {
+		title = title[:200]
+	}
+	content := "## Outcome\n" + outcome + "\n\n## Summary\n" + summary
+	kind := "investigation"
+	slug := "investigation:nomos/" + sessionID
+	tags := []string{"nomos-session", "auto-generated"}
+
+	// Upsert the knowledge entity.
+	docID, _ := uuid.NewV7()
+	if err := s.pool.QueryRow(ctx, `
+		INSERT INTO entities (id, slug, type, name, attributes)
+		VALUES ($1, $2, $3, $4, '{}')
+		ON CONFLICT (slug) DO UPDATE SET name = EXCLUDED.name, updated_at = now()
+		RETURNING id`, docID, slug, kind, title).Scan(&docID); err != nil {
+		slog.Warn("nomos: autoUpsertKnowledge entity insert", "session", sessionID, "error", err)
+		return
+	}
+
+	// Upsert the knowledge content.
+	if _, err := s.pool.Exec(ctx, `
+		INSERT INTO knowledge_entities (entity_id, title, content, source, tags, updated_at)
+		VALUES ($1, $2, $3, 'nomos-agent', $4, now())
+		ON CONFLICT (entity_id) DO UPDATE
+		  SET title = EXCLUDED.title, content = EXCLUDED.content,
+		      tags = EXCLUDED.tags, updated_at = now()`,
+		docID, title, content, tags); err != nil {
+		slog.Warn("nomos: autoUpsertKnowledge content insert", "session", sessionID, "error", err)
+		return
+	}
+
+	// Link to the task entity.
+	var taskEntID uuid.UUID
+	if s.pool.QueryRow(ctx, `SELECT entity_id FROM agent_sessions WHERE id = $1`,
+		sessionID).Scan(&taskEntID) == nil && taskEntID != uuid.Nil {
+		s.pool.Exec(ctx, `
+			INSERT INTO relationships (source_id, target_id, type, attributes, valid_from)
+			SELECT $1, $2, 'involves', '{"by":"nomos","auto":true}'::jsonb, now()
+			WHERE NOT EXISTS (
+				SELECT 1 FROM relationships
+				WHERE source_id = $1 AND target_id = $2 AND type = 'involves' AND valid_to IS NULL)`,
+			taskEntID, docID)
+	}
+
+	slog.Info("nomos: auto-upserted knowledge for session",
+		"session", sessionID, "outcome", outcome, "slug", slug)
+}
+
+// writePlanCompletionRate computes the step completion rate for the current
+// plan generation and writes it as a task entity attribute so the trend can
+// be tracked. Baseline from 2026-08-04 audit: 38% (15/39 steps reached done).
+func writePlanCompletionRate(ctx context.Context, s *store, sessionID string) {
+	var total, completed int
+	s.pool.QueryRow(ctx, `
+		SELECT COUNT(*), COALESCE(SUM(CASE WHEN status = 'done' THEN 1 ELSE 0 END), 0)
+		FROM session_plan_steps
+		WHERE session_id = $1
+		  AND generation = (SELECT MAX(generation) FROM session_plan_steps WHERE session_id = $1)
+		  AND status <> 'replaced'`, sessionID).Scan(&total, &completed)
+	if total > 0 {
+		rate := float64(completed) / float64(total)
+		attrs, _ := json.Marshal(map[string]any{"plan_completion_rate": rate, "plan_steps_total": total, "plan_steps_completed": completed})
+		s.pool.Exec(ctx, `
+			UPDATE entities SET attributes = attributes || $2::jsonb, updated_at = now()
+			WHERE id = (SELECT entity_id FROM agent_sessions WHERE id = $1)`,
+			sessionID, string(attrs))
+		slog.Info("nomos: plan completion rate", "session", sessionID, "rate", fmt.Sprintf("%.0f%%", rate*100),
+			"completed", completed, "total", total)
+	}
+}
+
+// autoFeedback creates a feedback entry linking the session's outcome to its
+// last execution, feeding the pattern-extraction pipeline that has been empty
+// since launch. Only created for success/partial outcomes (failures don't
+// have a specific execution to tie to).
+func autoFeedback(ctx context.Context, s *store, sessionID, outcome, summary string) {
+	// Find the last execution linked to this session.
+	var execID uuid.UUID
+	if err := s.pool.QueryRow(ctx, `
+		SELECT pe.execution_id FROM nomos_plan_executions pe
+		WHERE pe.session_id = $1::uuid
+		ORDER BY pe.created_at DESC LIMIT 1`, sessionID).Scan(&execID); err != nil || execID == uuid.Nil {
+		return
+	}
+	fbID, _ := uuid.NewV7()
+	slug := "feedback:" + fbID.String()
+	if _, err := s.pool.Exec(ctx, `
+		INSERT INTO entities (id, slug, type, name, attributes) VALUES ($1, $2, 'feedback', $3, '{}')`,
+		fbID, slug, "feedback for "+sessionID[:8]); err != nil {
+		slog.Warn("nomos: autoFeedback entity insert", "session", sessionID, "error", err)
+		return
+	}
+	_, err := s.pool.Exec(ctx, `
+		INSERT INTO feedback (entity_id, execution_id, outcome, observation, lesson, tags, created_at)
+		VALUES ($1, $2, $3, $4, $5, $6, now())`,
+		fbID, execID, outcome, summary, summary, []string{"nomos-session", "auto-generated", "session:" + sessionID[:8]})
+	if err != nil {
+		slog.Warn("nomos: autoFeedback insert", "session", sessionID, "error", err)
+		return
+	}
+	slog.Info("nomos: auto-feedback created for session", "session", sessionID, "outcome", outcome)
+}
+
 // blockerPatterns maps a substring (case-insensitive) to a structured blocker
 // reason. Order matters — earlier patterns take precedence. These are the
 // recurring failure signatures from the 2026-07-20 session audit. A
@@ -1310,6 +1467,53 @@ func (s *store) hadDiscovery(ctx context.Context, sessionID string) bool {
 	return count > 0
 }

+// sessionGoal returns the session's goal text, empty string if not found.
+// Used by complete_task to check whether the goal involved a reachability
+// verification before marking success.
+func (s *store) sessionGoal(ctx context.Context, sessionID string) string {
+	if s == nil || sessionID == "" {
+		return ""
+	}
+	var goal string
+	s.pool.QueryRow(ctx,
+		`SELECT COALESCE(goal, '') FROM agent_sessions WHERE id = $1`,
+		sessionID).Scan(&goal)
+	return goal
+}
+
+// hadRecentVerification checks whether the session successfully verified
+// reachability in recent turns — ping_service, or a run with curl/wget that
+// returned successfully. Used by complete_task as a soft warning when the
+// goal involved a reachability check but no recent verification occurred.
+func (s *store) hadRecentVerification(ctx context.Context, sessionID string) bool {
+	if s == nil || sessionID == "" {
+		return true // fail safe: don't warn when we can't check
+	}
+	// Check for ping_service calls in the last 5 activity entries for this session.
+	var pingCount int
+	s.pool.QueryRow(ctx, `
+		SELECT COUNT(*) FROM (
+			SELECT 1 FROM agent_activity
+			WHERE session_id = $1 AND tool_name = 'ping_service' AND success = true
+			ORDER BY ts DESC LIMIT 5
+		) sub`, sessionID).Scan(&pingCount)
+	if pingCount > 0 {
+		return true
+	}
+	// Check for run calls with curl/wget that returned successfully.
+	var curlCount int
+	s.pool.QueryRow(ctx, `
+		SELECT COUNT(*) FROM (
+			SELECT 1 FROM agent_activity
+			WHERE session_id = $1
+			  AND tool_name = 'run'
+			  AND success = true
+			  AND (input_summary LIKE '%curl%' OR input_summary LIKE '%wget%')
+			ORDER BY ts DESC LIMIT 10
+		) sub`, sessionID).Scan(&curlCount)
+	return curlCount > 0
+}
+
 // staleGoalSession is a goal-bearing task that's gone idle without reaching
 // a terminal state — the idle-sweep worker's work list (fix 2+3 of
 // plans/2026-07-11-task-completion-safety-net.md).
@@ -1913,7 +2117,7 @@ func (s *store) resolveArgEntityID(ctx context.Context, args map[string]any) uui
 // The (nullable) session_id column carries the conversation id. args is the
 // tool call's own arguments, used to best-effort tag the row with the
 // entity it acted on (see resolveArgEntityID).
-func (s *store) logActivity(ctx context.Context, agentID uuid.UUID, sessionID, toolName string, args map[string]any, inputSummary, outputSummary string, durationMs int, success bool, correlationID string) {
+func (s *store) logActivity(ctx context.Context, agentID uuid.UUID, sessionID, toolName string, args map[string]any, inputSummary, outputSummary string, durationMs int, success bool, correlationID string, tokenCount int) {
 	if s == nil || agentID == uuid.Nil {
 		return
 	}
@@ -1925,8 +2129,8 @@ func (s *store) logActivity(ctx context.Context, agentID uuid.UUID, sessionID, t
 	s.pool.Exec(ctx, `
 		INSERT INTO agent_activity
 		    (agent_id, session_id, activity_type, tool_name, entity_id, input_summary, output_summary,
-		     duration_ms, success, correlation_id)
-		VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10)`,
+		     duration_ms, success, correlation_id, token_count)
+		VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10, $11)`,
 		agentID, sessionID, "tool_call", toolName, entityIDArg, inputSummary, outputSummary,
-		durationMs, success, correlationID)
+		durationMs, success, correlationID, tokenCount)
 }
--- a/cmd/nomos/store_test.go
+++ b/cmd/nomos/store_test.go
@@ -192,7 +192,7 @@ func TestProposePlan_RefuseInFlight(t *testing.T) {
 	}

 	// Mark step 1 as started.
-	if err := s.updatePlanStep(ctx, sess.ID, 1, "running", ""); err != nil {
+	if err := s.updatePlanStep(ctx, sess.ID, 1, "running", "", ""); err != nil {
 		t.Fatalf("updatePlanStep: %v", err)
 	}

@@ -288,10 +288,10 @@ func TestUpdatePlanStep_GenerationRelative(t *testing.T) {

 	// The model addresses the new plan with 1-based seq. seq=1 must hit
 	// gen-2 "C", leaving gen-1 "A" (replaced) untouched.
-	if err := s.updatePlanStep(ctx, sess.ID, 1, "running", ""); err != nil {
+	if err := s.updatePlanStep(ctx, sess.ID, 1, "running", "", ""); err != nil {
 		t.Fatalf("updatePlanStep(seq=1, running): %v", err)
 	}
-	if err := s.updatePlanStep(ctx, sess.ID, 1, "done", ""); err != nil {
+	if err := s.updatePlanStep(ctx, sess.ID, 1, "done", "", ""); err != nil {
 		t.Fatalf("updatePlanStep(seq=1, done): %v", err)
 	}

@@ -319,7 +319,7 @@ func TestUpdatePlanStep_GenerationRelative(t *testing.T) {
 	}

 	// Out-of-range seq must be refused (no current-gen step there).
-	if err := s.updatePlanStep(ctx, sess.ID, 99, "running", ""); !errors.Is(err, errPlanStepNotFound) {
+	if err := s.updatePlanStep(ctx, sess.ID, 99, "running", "", ""); !errors.Is(err, errPlanStepNotFound) {
 		t.Fatalf("updatePlanStep(seq=99) err = %v, want errPlanStepNotFound", err)
 	}
 }
@@ -341,7 +341,7 @@ func TestCompleteTask_AutoCloseEmitsEvents(t *testing.T) {
 		t.Fatalf("proposePlan: %v", err)
 	}
 	// A is running, B still pending at completion time.
-	if err := s.updatePlanStep(ctx, sess.ID, 1, "running", ""); err != nil {
+	if err := s.updatePlanStep(ctx, sess.ID, 1, "running", "", ""); err != nil {
 		t.Fatalf("updatePlanStep(1, running): %v", err)
 	}
 	if err := s.completeTask(ctx, sess.ID, "success", "done"); err != nil {
@@ -397,7 +397,7 @@ func TestHadDiscoveryAndWriteback(t *testing.T) {

 	// A `run` call (discovery) — should set hadDiscovery, not hadEntityWriteback.
 	agentID := uuid.New()
-	s.logActivity(ctx, agentID, sess.ID, "run", nil, "", "uptime output", 100, true, "corr-1")
+	s.logActivity(ctx, agentID, sess.ID, "run", nil, "", "uptime output", 100, true, "corr-1", 0)
 	if !s.hadDiscovery(ctx, sess.ID) {
 		t.Fatal("hadDiscovery = false after a successful run call, want true")
 	}
@@ -410,7 +410,7 @@ func TestHadDiscoveryAndWriteback(t *testing.T) {
 	if err != nil {
 		t.Fatalf("createSession: %v", err)
 	}
-	s.logActivity(ctx, agentID, sess2.ID, "run", nil, "", "ssh timeout", 100, false, "corr-2")
+	s.logActivity(ctx, agentID, sess2.ID, "run", nil, "", "ssh timeout", 100, false, "corr-2", 0)
 	if s.hadDiscovery(ctx, sess2.ID) {
 		t.Fatal("hadDiscovery = true after a failed run call, want false (no facts learned)")
 	}
@@ -420,7 +420,7 @@ func TestHadDiscoveryAndWriteback(t *testing.T) {
 	if err != nil {
 		t.Fatalf("createSession: %v", err)
 	}
-	s.logActivity(ctx, agentID, sess3.ID, "get_entity", nil, "", "entity row", 10, true, "corr-3")
+	s.logActivity(ctx, agentID, sess3.ID, "get_entity", nil, "", "entity row", 10, true, "corr-3", 0)
 	if s.hadDiscovery(ctx, sess3.ID) {
 		t.Fatal("hadDiscovery = true after get_entity, want false (DB lookups are not discovery)")
 	}
@@ -430,12 +430,12 @@ func TestHadDiscoveryAndWriteback(t *testing.T) {
 	if err != nil {
 		t.Fatalf("createSession: %v", err)
 	}
-	s.logActivity(ctx, agentID, sess4.ID, "update_entity_attributes", nil, "", "ok", 10, true, "corr-4")
+	s.logActivity(ctx, agentID, sess4.ID, "update_entity_attributes", nil, "", "ok", 10, true, "corr-4", 0)
 	if !s.hadEntityWriteback(ctx, sess4.ID) {
 		t.Fatal("hadEntityWriteback = false after update_entity_attributes, want true")
 	}
 	// And the discovery+writeback combination (the conv3 scenario).
-	s.logActivity(ctx, agentID, sess4.ID, "run", nil, "", "apt-get update output", 100, true, "corr-5")
+	s.logActivity(ctx, agentID, sess4.ID, "run", nil, "", "apt-get update output", 100, true, "corr-5", 0)
 	if !s.hadDiscovery(ctx, sess4.ID) {
 		t.Fatal("hadDiscovery = false after run+writeback, want true")
 	}
--- a/cmd/nomos/tasks.go
+++ b/cmd/nomos/tasks.go
@@ -5,6 +5,7 @@ import (
 	"errors"
 	"fmt"
 	"log/slog"
+	"regexp"
 	"strings"
 	"time"
 )
@@ -306,7 +307,8 @@ func (a *agent) handleTaskTool(ctx context.Context, sessionID, name string, args
 		if seq <= 0 || status == "" {
 			return "error: update_plan_step needs seq (>=1) and status", true
 		}
-		if err := a.store.updatePlanStep(ctx, sessionID, seq, status, execID); err != nil {
+		reason, _ := args["replaced_reason"].(string)
+		if err := a.store.updatePlanStep(ctx, sessionID, seq, status, execID, reason); err != nil {
 			if errors.Is(err, errPlanStepNotFound) {
 				// The seq doesn't address a step in the CURRENT plan — most
 				// often a stale 1-based number the model carried across a
@@ -380,6 +382,12 @@ func (a *agent) handleTaskTool(ctx context.Context, sessionID, name string, args
 			return fmt.Sprintf("error completing task: %v", err), true
 		}
 		result := fmt.Sprintf("Task marked %s: %s", outcome, summary)
+		if outcome == "success" && a.store.hadDiscovery(ctx, sessionID) {
+			goal := a.store.sessionGoal(ctx, sessionID)
+			if mentionsReachability(goal) && !a.store.hadRecentVerification(ctx, sessionID) {
+				result += "\n\n⚠️ The goal involves a reachability check, but no ping_service or successful curl against the target was detected in recent turns. Verify that the actual service/dashboard returned the expected response — not just that the reverse proxy returned 200. Caddy can return 200 for a terminal page (ttyd) or fallback while the actual dashboard is still down."
+			}
+		}
 		if !a.store.hadEntityWriteback(ctx, sessionID) {
 			result += "\n\n⚠️ No entity attributes or relationships were updated in this session. Call update_entity_attributes and create_relationship to persist what you learned about entities before the next session starts from scratch."
 		}
@@ -389,6 +397,28 @@ func (a *agent) handleTaskTool(ctx context.Context, sessionID, name string, args
 	}
 }

+// reachabilityPatterns matches goal text that involves making something
+// reachable/accessible/working. Used by complete_task to surface a soft
+// warning when the session goal was about reachability but no verification
+// occurred before marking success.
+var reachabilityPatterns = []*regexp.Regexp{
+	regexp.MustCompile(`(?i)https?://[^\s]+`),
+	regexp.MustCompile(`(?i)\.hubris\.net\w+`),
+	regexp.MustCompile(`(?i)(un)?reachable`),
+	regexp.MustCompile(`(?i)(not?\s+)?(accessible|reachable|responding|resolving)`),
+	regexp.MustCompile(`(?i)diagnose\s+why`),
+	regexp.MustCompile(`(?i)(fix|restore|bring\s+back).*(accessible|reachable|online)`),
+}
+
+func mentionsReachability(goal string) bool {
+	for _, p := range reachabilityPatterns {
+		if p.MatchString(goal) {
+			return true
+		}
+	}
+	return false
+}
+
 // autoCompleteTrivialTask is the case-1 fix from
 // plans/2026-07-11-task-completion-safety-net.md: a session that never
 // called set_goal never framed itself as a structured task, so a turn that