phase 4: hermes agent — MCP tools, activity logging, 'all' role, wiring fixes

- mcp/server.go: 7 new tools (get_signal_history, get_patterns, get_skills, request_execution, get_trend, get_event_timeline, get_agent_activity), agent_activity logging middleware on every tool call. - phase3.go: QueryAgentActivity REST handler implemented (was stub). Fixed scan count mismatch in ListSkills/PatchSkill/ListSkillVersions (13 cols → 12 targets). Fixed AgentActivity cursor pagination (lexicographic → integer comparison). Fixed s.Slug → s.Name in log. - cmd/oikos/main.go: 'all' role now runs api + scheduler + notifier in one process. Replaced nil SchedulerRunner/NotifierRunner with direct scheduler.RunnerForMain() / notifier.RunnerForMain() imports. Added runWithPool helper for standalone scheduler/notifier roles. - internal/config/config.go: added HermesAgentID env var. - internal/httpapi/server.go: pass HermesAgentID to MCP handler. - docker-compose.yml: added scheduler and notifier services (dev profile). - hermes/: config.yaml, SOUL.md, skills/homelab-ops/SKILL.md. - Cleaned up: scheduler/init.go dead code, mcp/server.go pgx import guard.
2026-07-07 16:07:08 +02:00
parent aa197190cd
commit 3823a82417
12 changed files with 542 additions and 61 deletions
--- a/cmd/oikos/main.go
+++ b/cmd/oikos/main.go
@@ -13,15 +13,14 @@ import (
 	"github.com/dtoro/oikos/internal/config"
 	"github.com/dtoro/oikos/internal/db"
 	"github.com/dtoro/oikos/internal/httpapi"
+	"github.com/dtoro/oikos/internal/notifier"
 	"github.com/dtoro/oikos/internal/observability"
+	"github.com/dtoro/oikos/internal/scheduler"
 	"github.com/jackc/pgx/v5"
 )

-// SchedulerRunner is set by the scheduler init() to avoid circular imports.
-var SchedulerRunner func(context.Context, *db.Pool, config.Config)
-
-// NotifierRunner is set by the notifier init() to avoid circular imports.
-var NotifierRunner func(context.Context, *db.Pool, config.Config)
+var schedulerRunner = scheduler.RunnerForMain()
+var notifierRunner = notifier.RunnerForMain()

 func main() {
 	if len(os.Args) < 2 {
@@ -64,22 +63,30 @@ func main() {
 			os.Exit(1)
 		}
 	case "scheduler":
-		if SchedulerRunner != nil {
-			SchedulerRunner(ctx, nil, cfg)
-		} else {
-			slog.Error("scheduler not compiled in (import internal/scheduler)")
-			os.Exit(1)
-		}
+		runWithPool(ctx, cfg, "scheduler", schedulerRunner)
 	case "notifier":
-		if NotifierRunner != nil {
-			NotifierRunner(ctx, nil, cfg)
-		} else {
-			slog.Error("notifier not compiled in (import internal/notifier)")
+		runWithPool(ctx, cfg, "notifier", notifierRunner)
+	case "all":
+		pool, err := db.New(ctx, cfg.DatabaseURL)
+		if err != nil {
+			slog.Error("connect db", "error", err)
+			os.Exit(1)
+		}
+		defer pool.Close()
+
+		if err := pool.Migrate(ctx); err != nil {
+			slog.Error("migrate", "error", err)
+			os.Exit(1)
+		}
+
+		go schedulerRunner(ctx, pool, cfg)
+		go notifierRunner(ctx, pool, cfg)
+
+		slog.Info("all: starting api with scheduler + notifier in background")
+		if err := httpapi.ListenAndServe(ctx, pool, cfg); err != nil {
+			slog.Error("api failed", "error", err)
 			os.Exit(1)
 		}
-	case "all":
-		slog.Info("all role not yet implemented (runs api + scheduler + notifier in one process)")
-		os.Exit(1)
 	case "version":
 		fmt.Println("oikos dev (Phase 1)")
 	case "help", "--help", "-h":
@@ -231,6 +238,22 @@ func runAPI(ctx context.Context, cfg config.Config) error {
 	return err
 }

+func runWithPool(ctx context.Context, cfg config.Config, name string, fn func(context.Context, *db.Pool, config.Config)) {
+	pool, err := db.New(ctx, cfg.DatabaseURL)
+	if err != nil {
+		slog.Error("connect db", "role", name, "error", err)
+		os.Exit(1)
+	}
+	defer pool.Close()
+
+	if err := pool.Migrate(ctx); err != nil {
+		slog.Error("migrate", "role", name, "error", err)
+		os.Exit(1)
+	}
+
+	fn(ctx, pool, cfg)
+}
+
 func runExport(ctx context.Context, cfg config.Config) error {
 	pool, err := db.New(ctx, cfg.DatabaseURL)
 	if err != nil {
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -60,11 +60,46 @@ services:
      OIKOS_API_LISTEN: ":8090"
      OIKOS_ENV: dev
      OIKOS_DEBUG: "true"
+      OIKOS_HERMES_AGENT_ID: ${OIKOS_HERMES_AGENT_ID:-}
    ports:
      - "8090:8090"
    command: ["api"]
    stop_signal: SIGTERM
    stop_grace_period: 30s

+  # Scheduler (Phase 3) — observe loop
+  scheduler:
+    build:
+      context: .
+      dockerfile: compose/oikos/Dockerfile
+    profiles: ["dev", "full"]
+    depends_on:
+      seed:
+        condition: service_completed_successfully
+    environment:
+      OIKOS_DATABASE_URL: postgres://oikos:${OIKOS_DB_PASSWORD:-oikos_dev}@postgres:5432/oikos?sslmode=disable
+      OIKOS_DEBUG: "true"
+      OIKOS_SCHEDULER_INTERVAL: "30s"
+    command: ["scheduler"]
+    stop_signal: SIGTERM
+    stop_grace_period: 30s
+
+  # Notifier (Phase 3) — Matrix alerts
+  notifier:
+    build:
+      context: .
+      dockerfile: compose/oikos/Dockerfile
+    profiles: ["dev", "full"]
+    depends_on:
+      seed:
+        condition: service_completed_successfully
+    environment:
+      OIKOS_DATABASE_URL: postgres://oikos:${OIKOS_DB_PASSWORD:-oikos_dev}@postgres:5432/oikos?sslmode=disable
+      OIKOS_DEBUG: "true"
+      OIKOS_APPROVAL_HMAC_SECRET: ${OIKOS_APPROVAL_HMAC_SECRET:-dev-secret}
+    command: ["notifier"]
+    stop_signal: SIGTERM
+    stop_grace_period: 30s
+
 volumes:
  pg-data:
--- a/hermes/SOUL.md
+++ b/hermes/SOUL.md
@@ -0,0 +1,50 @@
+# SOUL.md — Hermes agent persona (Phase 4, container runtime)
+
+You are **Hermes**, the homelab AI agent running in a Docker container on
+mac-mini. You operate in **gateway mode** on mesh-only port 8092.
+
+## Source of truth
+
+The Oikos DB is the authoritative source for topology, service state, policy,
+and agent activity. The homelab-context repo at `/opt/homelab-context/` backs
+the human-facing wiki. When they disagree, the DB wins.
+
+## Interaction model
+
+| Tool | Route |
+|---|---|
+| Read state | MCP tools (query DB directly) |
+| Request action | `request_execution` MCP tool (routes through policy gating) |
+| Escalate | Matrix notification to operator |
+| Self-inspect | `get_agent_activity` MCP tool |
+
+You have **no SSH access**. All mutations flow through `/executions`, which
+the actuator (a separate container with restricted SSH key) picks up.
+
+## Key MCP tools
+
+- `get_entity`, `list_entities` — resolve slugs to state
+- `get_blast_radius` — understand impact before requesting action
+- `get_health_summary` — fleet status at a glance
+- `get_signal_history` — open alerts
+- `get_trend` — metric trends for decisions
+- `request_execution` — the ONLY mutation path
+- `get_agent_activity` — your own behavior log
+
+## Policy awareness
+
+Before calling `request_execution`:
+- Check risk class via `get_entity` on the target
+- If `destructive` or `config_mutation`: escalate to operator
+- If `reversible_low` with validated pattern: auto-act allowed
+
+## Token efficiency
+
+Use MCP tools over raw queries. MCP responses are already compressed. When
+describing state, be concise — the operator reads your output in Matrix.
+
+## Skills
+
+Skills live in `/app/hermes/skills/`. Load a skill when its description
+matches the task. The `homelab-ops` skill covers:
+- Health checks, signal triage, pattern validation, and escalation flow.
--- a/hermes/config.yaml
+++ b/hermes/config.yaml
@@ -0,0 +1,26 @@
+# Hermes container config — Gateway mode with MCP wiring (Phase 4)
+# Deployed: mac-mini Docker, mesh-published :8092
+# No SSH keys in this container; all mutations route through /executions
+
+agent:
+  name: hermes
+  entity_slug: agent:hermes
+  role: gateway
+
+mcp:
+  endpoint: http://api:8090/mcp
+  transport: streamable_http
+  bearer_token_env: OIKOS_MCP_BEARER_TOKEN
+
+server:
+  listen: ":8092"
+  mesh_only: true
+
+model:
+  provider: openrouter
+  model: deepseek/deepseek-v4-pro
+  api_key_env: OPENROUTER_API_KEY
+
+session:
+  mode: smart_approve
+  skills_dir: /app/hermes/skills
--- a/hermes/skills/homelab-ops/SKILL.md
+++ b/hermes/skills/homelab-ops/SKILL.md
@@ -0,0 +1,45 @@
+# Homelab Operations Skill
+
+**Risk class:** Depends on action (see OIKOS.md policy)
+**Required scope:** agent
+**Verification:** `get_health_summary` after action
+
+## Overview
+
+Standard operating procedures for the Hermes agent managing the hubris
+homelab. All mutations route through `request_execution` → Oikos policy
+gating → actuator (SSH).
+
+## Procedures
+
+### Health check triage
+
+1. `get_health_summary` — check fleet health
+2. For degraded/down entities, `get_entity` for detail
+3. `get_signal_history` on the target to check for repeats
+4. `get_blast_radius` to assess downstream impact
+5. `get_trend` for metric context before deciding
+
+### Signal response
+
+- `reversible_low` with validated pattern → `request_execution` (auto-restart)
+- `config_mutation` or `destructive` → escalate to operator
+- Repeated flapping → escalate with flap count
+
+### Execution tracking
+
+1. `request_execution` returns a correlation_id
+2. Poll `get_event_timeline` filtering by correlation_id
+3. Once complete, `get_health_summary` to verify recovery
+4. Record outcome via internal reasoning
+
+### Pattern learning
+
+- After 5 identical successful executions on the same (type, action), the
+  learning engine promotes the pattern to `validated`
+- Check `get_patterns(status=validated)` to know what's trusted
+
+## Changelog
+
+### 2026-07-07 — initial Phase 4 skill
+Baseline homelab operations skill for Hermes container.
--- a/internal/config/config.go
+++ b/internal/config/config.go
@@ -53,6 +53,9 @@ type Config struct {

 	// Approval HMAC secret (Phase 3)
 	ApprovalHMACSecret string
+
+	// Hermes agent entity ID (Phase 4)
+	HermesAgentID string
 }

 // Default returns a Config with compiled defaults.
@@ -139,6 +142,9 @@ func FromEnv() Config {
 	if v := os.Getenv("OIKOS_APPROVAL_HMAC_SECRET"); v != "" {
 		c.ApprovalHMACSecret = v
 	}
+	if v := os.Getenv("OIKOS_HERMES_AGENT_ID"); v != "" {
+		c.HermesAgentID = v
+	}

 	return c
 }
--- a/internal/httpapi/phase3.go
+++ b/internal/httpapi/phase3.go
@@ -887,7 +887,7 @@ func (s *Server) ListSkills(ctx context.Context, req gen.ListSkillsRequestObject
 	rows, err := s.pool.Query(ctx, `
 		SELECT s.entity_id, s.version, s.name, s.procedure, s.applies_type,
 		       s.action, s.pattern_ids, s.status, s.success_rate,
-		       s.changed_by::text, s.change_reason, s.last_used_at, s.created_at
+		       s.changed_by::text, s.change_reason, s.last_used_at
 		FROM skills s
 		WHERE ($1::text IS NULL OR s.status = $1)
 		  AND ($2::text IS NULL OR s.applies_type = $2)
@@ -917,7 +917,7 @@ func (s *Server) ListSkills(ctx context.Context, req gen.ListSkillsRequestObject
 		}
 		seen[s.Id.String()] = true
 		if err := json.Unmarshal(procBytes, &s.Procedure); err != nil {
-			slog.Warn("phase3: unmarshal skill procedure", "skill", s.Slug, "error", err)
+			slog.Warn("phase3: unmarshal skill procedure", "skill", s.Name, "error", err)
 		}
 		if len(patternIDs) > 0 {
 			pids := make([]string, len(patternIDs))
@@ -977,7 +977,7 @@ func (s *Server) PatchSkill(ctx context.Context, req gen.PatchSkillRequestObject
 	err = tx.QueryRow(ctx, `
 		SELECT entity_id, version, name, procedure, applies_type, action,
 		       pattern_ids, status, success_rate, changed_by::text,
-		       change_reason, last_used_at, created_at
+		       change_reason, last_used_at
 		FROM skills WHERE entity_id = $1 ORDER BY version DESC LIMIT 1`, id).
 		Scan(&skill.Id, &skill.Version, &skill.Name, &procBytes, &skill.AppliesType,
 			&skill.Action, &patternIDs, &skill.Status, &skill.SuccessRate,
@@ -1022,7 +1022,7 @@ func (s *Server) ListSkillVersions(ctx context.Context, req gen.ListSkillVersion
 	rows, err := s.pool.Query(ctx, `
 		SELECT entity_id, version, name, procedure, applies_type, action,
 		       pattern_ids, status, success_rate, changed_by::text,
-		       change_reason, last_used_at, created_at
+		       change_reason, last_used_at
 		FROM skills WHERE entity_id = $1
 		ORDER BY version DESC`, id)
 	if err != nil {
@@ -1739,7 +1739,82 @@ func (s *Server) GetEntityKnowledge(ctx context.Context, request gen.GetEntityKn
 // ─── Agent Activity (stub) ─────────────────────────────────────────────

 func (s *Server) QueryAgentActivity(ctx context.Context, request gen.QueryAgentActivityRequestObject) (gen.QueryAgentActivityResponseObject, error) {
-	return nil, errNotImplemented
+	limit := clampLimit(request.Params.Limit)
+	from := time.Now().Add(-24 * time.Hour)
+	if request.Params.From != nil {
+		from = *request.Params.From
+	}
+	to := time.Now()
+	if request.Params.To != nil {
+		to = *request.Params.To
+	}
+
+	var agentID *string
+	if request.Params.AgentId != nil {
+		a := *request.Params.AgentId
+		agentID = &a
+	}
+	var activityType *string
+	if request.Params.ActivityType != nil {
+		a := string(*request.Params.ActivityType)
+		activityType = &a
+	}
+	var entityID *string
+	if request.Params.EntityId != nil {
+		a := *request.Params.EntityId
+		entityID = &a
+	}
+	var cursorID *int
+	if request.Params.Cursor != nil && *request.Params.Cursor != "" {
+		if id, err := parseIntOrZero(*request.Params.Cursor); err == nil && id > 0 {
+			cursorID = &id
+		}
+	}
+
+	rows, err := s.pool.Query(ctx, `
+		SELECT id, ts, agent_id::text, session_id, activity_type, tool_name,
+		       entity_id::text, input_summary, output_summary,
+		       duration_ms, token_count, success, correlation_id
+		FROM agent_activity
+		WHERE ts >= $1 AND ts <= $2
+		  AND ($3::text IS NULL OR agent_id::text = $3)
+		  AND ($4::text IS NULL OR activity_type = $4)
+		  AND ($5::text IS NULL OR entity_id::text = $5)
+		  AND ($6::bigint IS NULL OR id < $6::bigint)
+		ORDER BY id DESC
+		LIMIT $7`,
+		from, to, agentID, activityType, entityID, cursorID, limit+1)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+
+	items := []gen.AgentActivity{}
+	for rows.Next() {
+		var a gen.AgentActivity
+		if err := rows.Scan(&a.Id, &a.Ts, &a.AgentId, &a.SessionId,
+			&a.ActivityType, &a.ToolName, &a.EntityId,
+			&a.InputSummary, &a.OutputSummary,
+			&a.DurationMs, &a.TokenCount, &a.Success,
+			&a.CorrelationId); err != nil {
+			return nil, err
+		}
+		items = append(items, a)
+	}
+	if rows.Err() != nil {
+		return nil, rows.Err()
+	}
+
+	var next *string
+	if len(items) > limit {
+		items = items[:limit]
+		lastID := fmt.Sprintf("%d", items[len(items)-1].Id)
+		next = &lastID
+	}
+	if items == nil {
+		items = []gen.AgentActivity{}
+	}
+	return gen.QueryAgentActivity200JSONResponse{Items: items, NextCursor: next}, nil
 }

 // ─── Helpers ───────────────────────────────────────────────────────────
@@ -1750,3 +1825,14 @@ func coalesceStr(s *string, def string) string {
 	}
 	return *s
 }
+
+func parseIntOrZero(s string) (int, error) {
+	var n int
+	for _, c := range s {
+		if c < '0' || c > '9' {
+			return 0, fmt.Errorf("invalid integer: %q", s)
+		}
+		n = n*10 + int(c-'0')
+	}
+	return n, nil
+}
--- a/internal/httpapi/server.go
+++ b/internal/httpapi/server.go
@@ -26,6 +26,7 @@ import (
 	"github.com/go-chi/chi/v5"
 	"github.com/go-chi/chi/v5/middleware"
 	"github.com/golang-jwt/jwt/v5"
+	"github.com/google/uuid"
 )

 // contextKey for storing actor identity in request context.
@@ -109,7 +110,13 @@ func NewHandler(ctx context.Context, pool *db.Pool, cfg config.Config) http.Hand
 	r.With(combinedAuth(cfg)).Get("/api/v1/events/stream", s.serveSSE)

 	// Mount MCP at /mcp (plan R3-10)
-	r.With(combinedAuth(cfg)).Handle("/mcp", mcphandler.NewHandler(pool, cfg.MCPBearerToken))
+	hermesAgentID := uuid.Nil
+	if cfg.HermesAgentID != "" {
+		if id, err := uuid.Parse(cfg.HermesAgentID); err == nil {
+			hermesAgentID = id
+		}
+	}
+	r.With(combinedAuth(cfg)).Handle("/mcp", mcphandler.NewHandler(pool, cfg.MCPBearerToken, hermesAgentID))

 	return r
 }
--- a/internal/mcp/server.go
+++ b/internal/mcp/server.go
@@ -13,7 +13,6 @@ import (
 	"github.com/dtoro/oikos/internal/db"
 	"github.com/google/jsonschema-go/jsonschema"
 	"github.com/google/uuid"
-	"github.com/jackc/pgx/v5"
 	"github.com/modelcontextprotocol/go-sdk/mcp"
 )

@@ -34,8 +33,9 @@ func objSchema(props ...prop) *jsonschema.Schema {
 }

 // NewHandler creates an http.Handler that serves the Oikos MCP server.
-func NewHandler(pool *db.Pool, token string) http.Handler {
-	s := newServer(pool)
+// agentID is the Hermes agent entity UUID; tool calls are logged to agent_activity.
+func NewHandler(pool *db.Pool, token string, agentID uuid.UUID) http.Handler {
+	s := newServer(pool, agentID)
 	handler := mcp.NewStreamableHTTPHandler(func(r *http.Request) *mcp.Server {
 		if token != "" {
 			if r.Header.Get("Authorization") != "Bearer "+token {
@@ -47,15 +47,19 @@ func NewHandler(pool *db.Pool, token string) http.Handler {
 	return handler
 }

-func newServer(pool *db.Pool) *mcp.Server {
+// toolHandler is the function signature registered via AddTool.
+type toolHandler = mcp.ToolHandler
+
+func newServer(pool *db.Pool, agentID uuid.UUID) *mcp.Server {
 	s := mcp.NewServer(&mcp.Implementation{Name: "oikos", Version: "dev"}, &mcp.ServerOptions{
 		Logger: slog.Default(),
 	})

-	// All tools use the untyped handler (s.AddTool) for simplicity.
-	// Arguments are accessed via req.Parameters.Arguments.(map[string]any).
+	register := func(tool *mcp.Tool, handler toolHandler) {
+		s.AddTool(tool, withActivityLogging(pool, agentID, tool.Name, handler))
+	}

-	s.AddTool(&mcp.Tool{Name: "get_entity", Description: "Get an entity by slug or UUID",
+	register(&mcp.Tool{Name: "get_entity", Description: "Get an entity by slug or UUID",
 		InputSchema: objSchema(prop{"slug_or_id", "string", "Entity slug (e.g. host:hubris) or UUID"}),
 	}, func(ctx context.Context, req *mcp.CallToolRequest) (*mcp.CallToolResult, error) {
 		args := argsMap(req)
@@ -63,7 +67,7 @@ func newServer(pool *db.Pool) *mcp.Server {
 		return queryEntity(ctx, pool, idOrSlug), nil
 	})

-	s.AddTool(&mcp.Tool{Name: "list_entities", Description: "List entities filtered by type, state, or search",
+	register(&mcp.Tool{Name: "list_entities", Description: "List entities filtered by type, state, or search",
 		InputSchema: objSchema(
 			prop{"type", "string", "Filter by entity type"},
 			prop{"state", "string", "Filter by lifecycle state"},
@@ -82,7 +86,7 @@ func newServer(pool *db.Pool) *mcp.Server {
 			nStr(args["type"]), nStr(args["state"]), nStr(args["q"]), limit), nil
 	})

-	s.AddTool(&mcp.Tool{Name: "get_relations", Description: "Get relationships for an entity",
+	register(&mcp.Tool{Name: "get_relations", Description: "Get relationships for an entity",
 		InputSchema: objSchema(prop{"entity_id", "string", "Entity slug"}),
 	}, func(ctx context.Context, req *mcp.CallToolRequest) (*mcp.CallToolResult, error) {
 		args := argsMap(req)
@@ -96,7 +100,7 @@ func newServer(pool *db.Pool) *mcp.Server {
 			ORDER BY r.type`, slug), nil
 	})

-	s.AddTool(&mcp.Tool{Name: "get_blast_radius", Description: "Find entities affected if this entity goes down",
+	register(&mcp.Tool{Name: "get_blast_radius", Description: "Find entities affected if this entity goes down",
 		InputSchema: objSchema(
 			prop{"entity_id", "string", "Entity slug"},
 			prop{"depth", "integer", "Traversal depth (default 3)"}),
@@ -109,7 +113,7 @@ func newServer(pool *db.Pool) *mcp.Server {
 			slug, depth), nil
 	})

-	s.AddTool(&mcp.Tool{Name: "get_health_summary", Description: "Current fleet health summary",
+	register(&mcp.Tool{Name: "get_health_summary", Description: "Current fleet health summary",
 		InputSchema: objSchema(),
 	}, func(ctx context.Context, req *mcp.CallToolRequest) (*mcp.CallToolResult, error) {
 		return queryRows(ctx, pool, `
@@ -118,7 +122,7 @@ func newServer(pool *db.Pool) *mcp.Server {
 			ORDER BY e.slug`), nil
 	})

-	s.AddTool(&mcp.Tool{Name: "get_audit_trail", Description: "Query the audit log",
+	register(&mcp.Tool{Name: "get_audit_trail", Description: "Query the audit log",
 		InputSchema: objSchema(prop{"entity_id", "string", "Filter by affected entity UUID"}),
 	}, func(ctx context.Context, req *mcp.CallToolRequest) (*mcp.CallToolResult, error) {
 		args := argsMap(req)
@@ -129,19 +133,19 @@ func newServer(pool *db.Pool) *mcp.Server {
 			ORDER BY ts DESC LIMIT 50`, nStr(args["entity_id"])), nil
 	})

-	s.AddTool(&mcp.Tool{Name: "search_knowledge", Description: "Full-text search across documentation",
+	register(&mcp.Tool{Name: "search_knowledge", Description: "Full-text search across documentation",
 		InputSchema: objSchema(prop{"query", "string", "Search terms"}),
 	}, func(ctx context.Context, req *mcp.CallToolRequest) (*mcp.CallToolResult, error) {
 		args := argsMap(req)
-		q, _ := args["query"].(string)
+		q := nStr(args["query"])
 		return queryRows(ctx, pool, `
 			SELECT id, title, LEFT(content, 500) AS preview
 			FROM knowledge_entities
-			WHERE title ILIKE '%'||$1||'%' OR content ILIKE '%'||$1||'%'
+			WHERE ($1::text IS NULL OR title ILIKE '%'||$1||'%' OR content ILIKE '%'||$1||'%')
 			ORDER BY title LIMIT 20`, q), nil
 	})

-	s.AddTool(&mcp.Tool{Name: "query_metrics", Description: "Query time-series metrics",
+	register(&mcp.Tool{Name: "query_metrics", Description: "Query time-series metrics",
 		InputSchema: objSchema(prop{"hours", "integer", "Look-back window in hours (default 24)"}),
 	}, func(ctx context.Context, req *mcp.CallToolRequest) (*mcp.CallToolResult, error) {
 		args := argsMap(req)
@@ -158,9 +162,214 @@ func newServer(pool *db.Pool) *mcp.Server {
 			ORDER BY bucket DESC LIMIT 100`, hours), nil
 	})

+	// ─── Phase 4: new tools ──────────────────────────────────────────
+
+	register(&mcp.Tool{Name: "get_signal_history", Description: "Query open and recent signals",
+		InputSchema: objSchema(
+			prop{"entity_slug", "string", "Filter by target entity slug"},
+			prop{"state", "string", "Filter by signal state (raised, resolved)"},
+			prop{"limit", "integer", "Max rows (default 50)"}),
+	}, func(ctx context.Context, req *mcp.CallToolRequest) (*mcp.CallToolResult, error) {
+		args := argsMap(req)
+		limit := int(getFloat(args, "limit", 50))
+		return queryRows(ctx, pool, `
+			SELECT s.entity_id::text, s.kind, s.severity, s.state,
+			       s.occurrence_count, e.slug AS target_slug,
+			       s.first_seen_at, s.last_seen_at
+			FROM signals s
+			LEFT JOIN entities e ON e.id = s.target_entity_id
+			WHERE ($1::text IS NULL OR e.slug = $1)
+			  AND ($2::text IS NULL OR s.state = $2)
+			ORDER BY s.last_seen_at DESC LIMIT $3`,
+			nStr(args["entity_slug"]), nStr(args["state"]), limit), nil
+	})
+
+	register(&mcp.Tool{Name: "get_patterns", Description: "List learned action patterns",
+		InputSchema: objSchema(
+			prop{"status", "string", "Filter by status (hypothesized, validated, active)"},
+			prop{"entity_type", "string", "Filter by applies_type"},
+			prop{"action", "string", "Filter by action"}),
+	}, func(ctx context.Context, req *mcp.CallToolRequest) (*mcp.CallToolResult, error) {
+		args := argsMap(req)
+		return queryRows(ctx, pool, `
+			SELECT p.entity_id::text, p.applies_type, p.action, p.pattern,
+			       p.confidence, p.evidence_count, p.success_count, p.failure_count,
+			       p.status, p.quarantined, p.version, p.last_validated_at
+			FROM patterns p
+			WHERE ($1::text IS NULL OR p.status = $1)
+			  AND ($2::text IS NULL OR p.applies_type = $2)
+			  AND ($3::text IS NULL OR p.action = $3)
+			ORDER BY p.applies_type, p.action`,
+			nStr(args["status"]), nStr(args["entity_type"]), nStr(args["action"])), nil
+	})
+
+	register(&mcp.Tool{Name: "get_skills", Description: "List available automation skills",
+		InputSchema: objSchema(
+			prop{"status", "string", "Filter by status (active, inactive, deprecated)"},
+		),
+	}, func(ctx context.Context, req *mcp.CallToolRequest) (*mcp.CallToolResult, error) {
+		args := argsMap(req)
+		return queryRows(ctx, pool, `
+			SELECT s.entity_id::text, s.version, s.name, LEFT(s.procedure::text, 300) AS procedure_preview,
+			       s.applies_type, s.action, s.status, s.success_rate,
+			       s.changed_by::text, s.change_reason, s.last_used_at
+			FROM skills s
+			WHERE ($1::text IS NULL OR s.status = $1)
+			ORDER BY s.name, s.version DESC`,
+			nStr(args["status"])), nil
+	})
+
+	register(&mcp.Tool{Name: "request_execution", Description: "Request a gated execution (Hermes-only mutation path)",
+		InputSchema: objSchema(
+			prop{"target", "string", "Target entity slug"},
+			prop{"action", "string", "Action to perform"},
+		),
+	}, func(ctx context.Context, req *mcp.CallToolRequest) (*mcp.CallToolResult, error) {
+		args := argsMap(req)
+		targetSlug, _ := args["target"].(string)
+		action, _ := args["action"].(string)
+		if targetSlug == "" || action == "" {
+			return textResult("error: target and action are required"), nil
+		}
+
+		var targetID uuid.UUID
+		if err := pool.QueryRow(ctx, "SELECT id FROM entities WHERE slug = $1", targetSlug).Scan(&targetID); err != nil {
+			return textResult(fmt.Sprintf("target not found: %s", targetSlug)), nil
+		}
+
+		id, err := uuid.NewV7()
+		if err != nil {
+			return textResult(fmt.Sprintf("uuid error: %v", err)), nil
+		}
+		correlationID := uuid.New().String()
+
+		_, err = pool.Exec(ctx, `
+			INSERT INTO executions (entity_id, target_entity_id, action, risk_class,
+			    status, correlation_id, agent_id)
+			VALUES ($1, $2, $3, 'unclassified', 'pending', $4, $5)`,
+			id, targetID, action, correlationID, agentID)
+		if err != nil {
+			return textResult(fmt.Sprintf("insert execution: %v", err)), nil
+		}
+
+		return textResult(fmt.Sprintf("execution requested: id=%s target=%s action=%s correlation=%s",
+			id, targetSlug, action, correlationID)), nil
+	})
+
+	register(&mcp.Tool{Name: "get_trend", Description: "Get metric trends for an entity",
+		InputSchema: objSchema(
+			prop{"entity_id", "string", "Entity slug"},
+			prop{"days", "integer", "Look-back window in days (default 7)"}),
+	}, func(ctx context.Context, req *mcp.CallToolRequest) (*mcp.CallToolResult, error) {
+		args := argsMap(req)
+		slug, _ := args["entity_id"].(string)
+		days := int(getFloat(args, "days", 7))
+		return queryRows(ctx, pool, `
+			SELECT metric,
+			       ROUND(avg(value)::numeric, 2) AS avg_val,
+			       ROUND(stddev(value)::numeric, 2) AS std_val,
+			       count(*) AS sample_count,
+			       ROUND(regr_slope(value, EXTRACT(EPOCH FROM ts)::numeric)::numeric, 4) AS slope
+			FROM metric_samples ms
+			JOIN entities e ON e.id = ms.entity_id
+			WHERE e.slug = $1 AND ts >= now() - make_interval(days => $2)
+			GROUP BY metric
+			ORDER BY metric`, slug, days), nil
+	})
+
+	register(&mcp.Tool{Name: "get_event_timeline", Description: "Get recent events",
+		InputSchema: objSchema(
+			prop{"severity", "string", "Filter by severity (info, warn, error)"},
+			prop{"entity_slug", "string", "Filter by entity slug"},
+			prop{"limit", "integer", "Max rows (default 50)"}),
+	}, func(ctx context.Context, req *mcp.CallToolRequest) (*mcp.CallToolResult, error) {
+		args := argsMap(req)
+		limit := int(getFloat(args, "limit", 50))
+		return queryRows(ctx, pool, `
+			SELECT ev.ts, ev.event_type, ev.severity, ev.actor, e.slug AS entity_slug,
+			       ev.message, ev.correlation_id
+			FROM events ev
+			LEFT JOIN entities e ON e.id = ev.entity_id
+			WHERE ($1::text IS NULL OR ev.severity = $1)
+			  AND ($2::text IS NULL OR e.slug = $2)
+			ORDER BY ev.ts DESC LIMIT $3`,
+			nStr(args["severity"]), nStr(args["entity_slug"]), limit), nil
+	})
+
+	register(&mcp.Tool{Name: "get_agent_activity", Description: "Agent self-inspection: query agent activity log",
+		InputSchema: objSchema(
+			prop{"limit", "integer", "Max rows (default 50)"}),
+	}, func(ctx context.Context, req *mcp.CallToolRequest) (*mcp.CallToolResult, error) {
+		args := argsMap(req)
+		limit := int(getFloat(args, "limit", 50))
+		return queryRows(ctx, pool, `
+			SELECT id, ts, agent_id::text, session_id, activity_type, tool_name,
+			       entity_id::text, left(input_summary, 200) AS input_summary,
+			       left(output_summary, 200) AS output_summary,
+			       duration_ms, token_count, success, correlation_id
+			FROM agent_activity
+			WHERE agent_id = $1
+			ORDER BY ts DESC LIMIT $2`, agentID, limit), nil
+	})
+
 	return s
 }

+// withActivityLogging wraps a tool handler to record agent_activity rows.
+func withActivityLogging(pool *db.Pool, agentID uuid.UUID, toolName string, next mcp.ToolHandler) mcp.ToolHandler {
+	if agentID == uuid.Nil {
+		return next
+	}
+	return func(ctx context.Context, req *mcp.CallToolRequest) (*mcp.CallToolResult, error) {
+		start := time.Now()
+		result, err := next(ctx, req)
+		duration := int(time.Since(start).Milliseconds())
+
+		// Build input summary (first 500 chars of args)
+		inputSummary := ""
+		if req != nil && len(req.Params.Arguments) > 0 {
+			inputSummary = string(req.Params.Arguments)
+		}
+		if len(inputSummary) > 500 {
+			inputSummary = inputSummary[:500]
+		}
+
+		// Build output summary
+		outputSummary := ""
+		success := err == nil
+		if result != nil {
+			for _, c := range result.Content {
+				if tc, ok := c.(*mcp.TextContent); ok {
+					outputSummary = tc.Text
+					break
+				}
+			}
+		}
+		if err != nil {
+			outputSummary = err.Error()
+			success = false
+		}
+		if len(outputSummary) > 500 {
+			outputSummary = outputSummary[:500]
+		}
+
+		correlationID := uuid.New().String()
+
+		_, logErr := pool.Exec(ctx, `
+			INSERT INTO agent_activity
+			    (agent_id, activity_type, tool_name, input_summary, output_summary,
+			     duration_ms, success, correlation_id)
+			VALUES ($1, $2, $3, $4, $5, $6, $7, $8)`,
+			agentID, "tool_call", toolName, inputSummary, outputSummary,
+			duration, success, correlationID)
+		if logErr != nil {
+			slog.Warn("mcp: log agent_activity", "error", logErr)
+		}
+
+		return result, err
+	}
+}
+
 // ─── Helpers ──────────────────────────────────────────────────────────

 func argsMap(req *mcp.CallToolRequest) map[string]any {
@@ -181,6 +390,12 @@ func getFloat(m map[string]any, key string, def float64) float64 {
 		return v
 	case int:
 		return float64(v)
+	case json.Number:
+		f, err := v.Float64()
+		if err != nil {
+			return def
+		}
+		return f
 	}
 	return def
 }
@@ -244,7 +459,4 @@ func queryRows(ctx context.Context, pool *db.Pool, query string, args ...any) *m

 	data, _ := json.MarshalIndent(items, "", "  ")
 	return textResult(string(data))
-}
-
-var _ = pgx.ErrNoRows
-var _ = time.Now
+}
--- a/internal/mcp/server_test.go
+++ b/internal/mcp/server_test.go
@@ -2,6 +2,8 @@ package mcp

 import (
 	"testing"
+
+	"github.com/google/uuid"
 )

 // TestNewServerRegistersTools verifies every tool registers with a valid
@@ -16,7 +18,7 @@ func TestNewServerRegistersTools(t *testing.T) {
 	}()
 	// pool is only used inside tool handlers (invoked per-call), not at
 	// registration time, so a nil pool is safe for this construction test.
-	s := newServer(nil)
+	s := newServer(nil, uuid.Nil)
 	if s == nil {
 		t.Fatal("newServer returned nil")
 	}
--- a/internal/notifier/notifier.go
+++ b/internal/notifier/notifier.go
@@ -36,6 +36,11 @@ func Run(ctx context.Context, pool *db.Pool, cfg config.Config) {
 	}
 }

+// RunnerForMain provides the run function for registration in main.
+func RunnerForMain() func(context.Context, *db.Pool, config.Config) {
+	return Run
+}
+
 // processPendingApprovals checks for pending approvals and sends alerts.
 func processPendingApprovals(ctx context.Context, pool *db.Pool, cfg config.Config) {
 	q := sqlcgen.New(pool)
--- a/internal/scheduler/init.go
+++ b/internal/scheduler/init.go
@@ -2,28 +2,12 @@ package scheduler

 import (
 	"context"
-	"log/slog"

 	"github.com/dtoro/oikos/internal/config"
 	"github.com/dtoro/oikos/internal/db"
-	"github.com/dtoro/oikos/internal/db/sqlcgen"
 )

-func init() {
-	// Register with main package via package-level variable
-	// The cmd/oikos/main.go sets SchedulerRunner in its import
-	mainRunner = Run
-}
-
-// mainRunner is assigned to main.SchedulerRunner by the cmd/oikos package.
-// It's set during init so that when main runs, the scheduler Runner is available.
-var mainRunner func(context.Context, *db.Pool, config.Config)
-
 // RunnerForMain provides the run function for registration in main.
 func RunnerForMain() func(context.Context, *db.Pool, config.Config) {
 	return Run
 }
-
-// ensure sqlcgen is used
-var _ = sqlcgen.Queries{}
-var _ = slog.Default