cmd/mavend/ecosystem_trace_test.go

@@ -2,7 +2,6 @@ package main
 
 import (
 	"context"
-	"encoding/json"
 	"strings"
 	"testing"
 
@@ -11,34 +10,12 @@ import (
 
 // Versioning, authentication and tracing of ecosystem calls (Vikunja #273).
 
-func ecoTraces(t *testing.T, h *reactiveHandler) []map[string]any {
+func findTrace(t *testing.T, h *reactiveHandler, service, op string) *store.EcosystemTrace {
 	t.Helper()
-	facts, err := h.dataStore.RecentFacts(context.Background(), 100)
-	if err != nil {
-		t.Fatalf("read facts: %v", err)
-	}
-	var out []map[string]any
-	for _, f := range facts {
-		if f.Source != "ecosystem:trace" {
-			continue
-		}
-		i := strings.Index(f.Value, "{")
-		if i < 0 {
-			t.Fatalf("trace fact carries no detail object: %q", f.Value)
-		}
-		var d map[string]any
-		if err := json.Unmarshal([]byte(f.Value[i:]), &d); err != nil {
-			t.Fatalf("decode trace %q: %v", f.Value, err)
-		}
-		out = append(out, d)
-	}
-	return out
-}
-
-func findTrace(traces []map[string]any, service, op string) map[string]any {
-	for _, d := range traces {
-		if d["service"] == service && d["operation"] == op {
-			return d
+	for _, tr := range traces(t, h) {
+		if tr.Service == service && tr.Operation == op {
+			found := tr
+			return &found
 		}
 	}
 	return nil
@@ -58,7 +35,9 @@ func TestEcosystemHeaders_VersionRequesterAndAuth(t *testing.T) {
 	if err != nil {
 		t.Fatalf("resolve: %v", err)
 	}
-	if _, err := h.ecosystem.praxis.ListAttention(ctx, 5); err != nil {
+	// A bare client call carries whatever the caller assigned. Entry points
+	// assign the ID, the header layer only reads it, so mirror an action here.
+	if _, err := h.ecosystem.praxis.ListAttention(withCorrelationID(ctx, newCorrelationID()), 5); err != nil {
 		t.Fatalf("attention: %v", err)
 	}
 
@@ -167,31 +146,69 @@ func TestEcosystemTrace_SuccessfulActionTracesEveryHop(t *testing.T) {
 		t.Fatalf("setup: expected success, got %q", reply)
 	}
 
-	traces := ecoTraces(t, h)
+	var chain string
 	for _, want := range [][2]string{{"nexus", "resolve"}, {"hexis", "capabilities"}, {"hexis", "execute"}} {
-		d := findTrace(traces, want[0], want[1])
+		d := findTrace(t, h, want[0], want[1])
 		if d == nil {
-			t.Fatalf("missing trace for %s %s, got %+v", want[0], want[1], traces)
+			t.Fatalf("missing trace for %s %s, got %+v", want[0], want[1], traces(t, h))
 		}
-		if d["status"] != traceOK {
-			t.Errorf("%s %s status = %v, want ok", want[0], want[1], d["status"])
+		if d.Status != traceOK {
+			t.Errorf("%s %s status = %v, want ok", want[0], want[1], d.Status)
 		}
-		if _, ok := d["duration_ms"]; !ok {
-			t.Errorf("%s %s trace has no timing", want[0], want[1])
-		}
-		if d["correlation_id"] == nil || d["correlation_id"] == "" {
+		if d.CorrelationID == "" {
 			t.Errorf("%s %s trace has no correlation id", want[0], want[1])
 		}
+		if want[1] != "execute" {
+			if chain == "" {
+				chain = d.CorrelationID
+			} else if d.CorrelationID != chain {
+				t.Errorf("%s %s left the correlation chain: %s != %s", want[0], want[1], d.CorrelationID, chain)
+			}
+		}
 	}
-	exec := findTrace(traces, "hexis", "execute")
-	if exec["causation_id"] == nil || exec["causation_id"] == "" {
+	exec := findTrace(t, h, "hexis", "execute")
+	if exec.CausationID == "" {
 		t.Error("execute trace must carry the causation id of the turn that caused it")
 	}
-	if exec["correlation_id"] == exec["causation_id"] {
+	if exec.CorrelationID == exec.CausationID {
 		t.Error("execute correlation and causation must be distinguishable")
 	}
 }
 
+// TestEcosystemTrace_OneCorrelationIDPerPraxisAction: a digest calls attention
+// once and surface once per item. All of it is one turn, so the far side must
+// see one ID and not N+1 unrelated ones.
+func TestEcosystemTrace_OneCorrelationIDPerPraxisAction(t *testing.T) {
+	ctx := context.Background()
+	praxis := newFakePraxis(t, fixturePraxisAttentionItems(
+		map[string]any{"id": "item_1", "title": "disk almost full", "importance": 3.0},
+		map[string]any{"id": "item_2", "title": "backup is stale", "importance": 2.0},
+	))
+	h := ecoHandler(t, nil, praxis, nil)
+
+	if reply := h.handlePraxisAct(ctx, praxisActDec("list_attention")); !strings.Contains(reply, "disk almost full") {
+		t.Fatalf("setup: expected the digest, got %q", reply)
+	}
+
+	reqs := praxis.Requests()
+	if len(reqs) < 3 {
+		t.Fatalf("expected attention plus one surface per item, got %d requests", len(reqs))
+	}
+	first := reqs[0].Header.Get("X-Correlation-ID")
+	if first == "" {
+		t.Fatal("every ecosystem request must carry a correlation id")
+	}
+	for _, r := range reqs {
+		if got := r.Header.Get("X-Correlation-ID"); got != first {
+			t.Fatalf("%s %s carried %q, want the action's id %q", r.Method, r.Path, got, first)
+		}
+	}
+	tr := findTrace(t, h, "praxis", "list_attention")
+	if tr == nil || tr.CorrelationID != first {
+		t.Fatalf("the trace must carry the id that was actually sent, got %+v", tr)
+	}
+}
+
 // TestEcosystemTrace_FailuresAreTracedToo: the whole point of the change —
 // a failed hop is exactly the one worth having recorded.
 func TestEcosystemTrace_FailuresAreTracedToo(t *testing.T) {
@@ -203,18 +220,39 @@ func TestEcosystemTrace_FailuresAreTracedToo(t *testing.T) {
 
 	_ = h.handleHexisAct(ctx, actDec("muzick indexer"))
 
-	d := findTrace(ecoTraces(t, h), "nexus", "resolve")
+	d := findTrace(t, h, "nexus", "resolve")
 	if d == nil {
 		t.Fatal("a failed resolve must still be traced")
 	}
-	if d["status"] != traceFailed {
-		t.Errorf("status = %v, want failed", d["status"])
+	if d.Status != traceRefused {
+		t.Errorf("status = %v, want refused: the far side answered", d.Status)
 	}
-	if d["class"] != "unauthorized" {
-		t.Errorf("class = %v, want unauthorized", d["class"])
+	if d.Fields["class"] != "unauthorized" {
+		t.Errorf("class = %v, want unauthorized", d.Fields["class"])
 	}
-	if d["http_status"] != float64(401) {
-		t.Errorf("http_status = %v, want 401", d["http_status"])
+	if d.HTTPStatus != 401 {
+		t.Errorf("http_status = %v, want 401", d.HTTPStatus)
+	}
+}
+
+// TestEcosystemTrace_UnreachableIsNotRefused: never got an answer and answered
+// with a refusal are different failures, and the trace must say which.
+func TestEcosystemTrace_UnreachableIsNotRefused(t *testing.T) {
+	ctx := context.Background()
+	h := ecoHandler(t, nil, nil, nil)
+	h.ecosystem.nexus = newNexusClient("http://127.0.0.1:1")
+
+	_ = h.handleHexisAct(ctx, actDec("muzick indexer"))
+
+	d := findTrace(t, h, "nexus", "resolve")
+	if d == nil {
+		t.Fatal("an unreachable resolve must still be traced")
+	}
+	if d.Status != traceFailed {
+		t.Errorf("status = %v, want failed", d.Status)
+	}
+	if d.Fields["class"] != "unreachable" {
+		t.Errorf("class = %v, want unreachable", d.Fields["class"])
 	}
 }
 
@@ -227,28 +265,23 @@ func TestEcosystemTrace_RedactsTheUtterance(t *testing.T) {
 
 	_ = h.handleHexisAct(ctx, actDec("перезапусти кофемашину"))
 
-	facts, err := h.dataStore.RecentFacts(ctx, 100)
-	if err != nil {
-		t.Fatalf("read facts: %v", err)
-	}
-	var traced []store.Fact
-	for _, f := range facts {
-		if f.Source == "ecosystem:trace" {
-			traced = append(traced, f)
-		}
-		if strings.Contains(f.Value, "кофемашину") && f.Source == "ecosystem:trace" {
-			t.Fatalf("trace leaked the utterance: %q", f.Value)
-		}
-	}
-	if len(traced) == 0 {
+	recorded := traces(t, h)
+	if len(recorded) == 0 {
 		t.Fatal("expected a not_found resolve trace")
 	}
-	d := findTrace(ecoTraces(t, h), "nexus", "resolve")
-	if d["status"] != traceNotFound {
-		t.Errorf("status = %v, want not_found", d["status"])
+	for _, tr := range recorded {
+		for k, v := range tr.Fields {
+			if s, ok := v.(string); ok && strings.Contains(s, "кофемашину") {
+				t.Fatalf("trace leaked the utterance in %s: %q", k, s)
+			}
+		}
 	}
-	if d["subject"] != redactSubject("перезапусти кофемашину") {
-		t.Errorf("subject = %v, want a redacted length", d["subject"])
+	d := findTrace(t, h, "nexus", "resolve")
+	if d.Status != traceNotFound {
+		t.Errorf("status = %v, want not_found", d.Status)
+	}
+	if d.Fields["subject"] != redactSubject("перезапусти кофемашину") {
+		t.Errorf("subject = %v, want a redacted length", d.Fields["subject"])
 	}
 }
 
@@ -263,7 +296,7 @@ func TestEcosystemTrace_AmbiguityAndConfirmationAreRecorded(t *testing.T) {
 	hexis := newFakeHexis(t, restartCaps(), fixtureHexisExecuted("exec_1", "succeeded"))
 	h := ecoHandler(t, ambig, nil, hexis)
 	_ = h.handleHexisAct(ctx, actDec("muzick"))
-	if d := findTrace(ecoTraces(t, h), "nexus", "resolve"); d == nil || d["status"] != traceAmbig {
+	if d := findTrace(t, h, "nexus", "resolve"); d == nil || d.Status != traceAmbig {
 		t.Fatalf("ambiguous resolve must be traced as such, got %+v", d)
 	}
 
@@ -271,7 +304,13 @@ func TestEcosystemTrace_AmbiguityAndConfirmationAreRecorded(t *testing.T) {
 	mutating := fixtureHexisCapabilities(map[string]any{"id": "cap_restart", "name": "restart", "read_only": false})
 	h2 := ecoHandler(t, nexus, nil, newFakeHexis(t, mutating, fixtureHexisExecuted("exec_1", "succeeded")))
 	_ = h2.handleHexisAct(ctx, actDec("restart"))
-	if d := findTrace(ecoTraces(t, h2), "hexis", "confirmation"); d == nil || d["status"] != "pending" {
+	d := findTrace(t, h2, "hexis", "confirmation")
+	if d == nil || d.Status != tracePending {
 		t.Fatalf("a parked confirmation must be traced, got %+v", d)
 	}
+	// The confirmation hop is measured from the top of the action, not from
+	// the instant it is recorded, which was always zero.
+	if d.DurationMs == 0 {
+		t.Error("the confirmation trace must report the time the action took to get there")
+	}
 }

cmd/mavweb/ecosystem.go

@@ -8,6 +8,8 @@ import (
 	"net/http"
 	"sync"
 	"time"
+
+	"github.com/kami/maven/internal/ipc"
 )
 
 // The three sibling services Maven coordinates are headless JSON APIs (no web UI
@@ -84,9 +86,13 @@ type ecoData struct {
 	Nexus  ecoPanel[ecoEntity]
 	Praxis ecoPanel[ecoItem]
 	Hexis  ecoPanel[ecoCap]
+	Calls  ecoPanel[ipc.EcosystemTrace]
 }
 
-func handleEcosystem(w http.ResponseWriter, r *http.Request, urls ecoURLs) {
+// handleEcosystem renders the three sibling panels plus Maven's own log of the
+// calls she made to them. The call log comes from core, not from the siblings:
+// it is what Maven saw, including the hops that never got an answer.
+func handleEcosystem(w http.ResponseWriter, r *http.Request, urls ecoURLs, core ipc.CoreAPI) {
 	ctx := r.Context()
 	var d ecoData
 	var wg sync.WaitGroup
@@ -102,6 +108,15 @@ func handleEcosystem(w http.ResponseWriter, r *http.Request, urls ecoURLs) {
 	go func() { defer wg.Done(); d.Hexis.Err = getEco(ctx, urls.hexis, "/api/v1/capabilities", &d.Hexis.Rows) }()
 	wg.Wait()
 
+	if core == nil {
+		d.Calls.Err = "not configured"
+	} else if rows, err := core.RecentEcosystemTraces(ctx, 50); err != nil {
+		log.Printf("ecosystem traces: %v", err)
+		d.Calls.Err = "core read failed"
+	} else {
+		d.Calls.Rows = rows
+	}
+
 	w.Header().Set("Content-Type", "text/html; charset=utf-8")
 	if err := ecosystemTmpl.Execute(w, d); err != nil {
 		log.Printf("ecosystem render: %v", err)

cmd/mavweb/ecosystem.html

@@ -41,11 +41,24 @@
 {{end}}
 </section>
 
+<section class=card id=eco-calls>
+<div class=section-header>
+<h2>Calls <span class=card-sub>what Maven asked them</span></h2>
+</div>
+{{with .Calls}}
+{{if .Err}}<div class=empty>calls — {{.Err}}</div>
+{{else if not .Rows}}<div class=empty>no ecosystem calls yet.</div>
+{{else}}<div class=scroll><table class=mono><tr><th>when<th>service<th>operation<th>status<th>ms<th>http<th>correlation</tr>
+{{range .Rows}}<tr><td>{{ago .Ts}}<td><span class=badge>{{.Service}}</span><td class=en>{{.Operation}}<td>{{if eq .Status "ok"}}<span class="badge badge-ok">ok</span>{{else}}<span class="badge badge-warn">{{.Status}}</span>{{end}}<td>{{.DurationMs}}<td>{{if .HTTPStatus}}{{.HTTPStatus}}{{else}}—{{end}}<td class=key>{{.CorrelationID}}</tr>{{end}}
+</table></div>{{end}}
+{{end}}
+</section>
+
 {{template "shellBottom"}}
 <script>
 setInterval(() => fetch('/ecosystem').then(r => r.text()).then(html => {
   const d = new DOMParser().parseFromString(html, 'text/html');
-  for (const id of ['eco-nexus', 'eco-praxis', 'eco-hexis']) {
+  for (const id of ['eco-nexus', 'eco-praxis', 'eco-hexis', 'eco-calls']) {
     const old = document.getElementById(id), nu = d.getElementById(id);
     if (old && nu) old.replaceWith(nu);
   }

cmd/mavweb/main.go

@@ -443,7 +443,7 @@ func main() {
 	})
 	ecoURLsCfg := ecoURLs{nexus: *nexusURL, praxis: *praxisURL, hexis: *hexisURL}
 	mux.HandleFunc("/ecosystem", func(w http.ResponseWriter, r *http.Request) {
-		handleEcosystem(w, r, ecoURLsCfg)
+		handleEcosystem(w, r, ecoURLsCfg, core)
 	})
 	// ----- passkey (WebAuthn) endpoints -----
 	// Wired when both -core and a configured origin are present. The origin

internal/ipc/api.go

@@ -24,6 +24,23 @@ type Fact struct {
 	VoidsID    *int64    `json:"voids_id,omitempty"`
 }
 
+// EcosystemTrace — one hop of a cross-service ecosystem call, read by the
+// monitoring surfaces. Traces live in their own store table, not in facts:
+// they are written at machine rate and would otherwise crowd every bounded
+// reader of facts.
+type EcosystemTrace struct {
+	ID            int64          `json:"id"`
+	Ts            time.Time      `json:"ts"`
+	Service       string         `json:"service"`
+	Operation     string         `json:"operation"`
+	Status        string         `json:"status"`
+	DurationMs    int64          `json:"duration_ms"`
+	CorrelationID string         `json:"correlation_id"`
+	CausationID   string         `json:"causation_id"`
+	HTTPStatus    int            `json:"http_status"`
+	Fields        map[string]any `json:"fields,omitempty"`
+}
+
 // Bucket — presence hysteresis state: "present" | "away".
 type Bucket string
 
@@ -588,6 +605,10 @@ type CoreAPI interface {
 	RecentFacts(ctx context.Context, n int) ([]Fact, error)
 	CalendarEvents(ctx context.Context, from, to time.Time) ([]Fact, error)
 	RecentNudges(ctx context.Context, n int) ([]Nudge, error)
+
+	// RecentEcosystemTraces reads the ecosystem call log, which lives in its
+	// own table so machine-rate traces never crowd out human-rate facts.
+	RecentEcosystemTraces(ctx context.Context, n int) ([]EcosystemTrace, error)
 	WriteNote(ctx context.Context, ts time.Time, text string, embedding []float32, source string) (int64, error)
 	QueryNotes(ctx context.Context, embedding []float32, k int) ([]Note, error)
 	RecentNotes(ctx context.Context, n int) ([]Note, error)

internal/ipc/client.go

@@ -64,6 +64,7 @@ var readOnlyMethods = map[Method]bool{
 	MethodRecentFacts:          true,
 	MethodCalendarEvents:       true,
 	MethodRecentNudges:         true,
+	MethodRecentEcoTraces:      true,
 	MethodQueryNotes:           true,
 	MethodRecentNotes:          true,
 	MethodLookupTool:           true,
@@ -342,6 +343,14 @@ func (c *Client) CalendarEvents(ctx context.Context, from, to time.Time) ([]Fact
 	return out, nil
 }
 
+func (c *Client) RecentEcosystemTraces(ctx context.Context, n int) ([]EcosystemTrace, error) {
+	var out []EcosystemTrace
+	if err := c.call(ctx, MethodRecentEcoTraces, nReq{N: n}, &out); err != nil {
+		return nil, err
+	}
+	return out, nil
+}
+
 func (c *Client) RecentNudges(ctx context.Context, n int) ([]Nudge, error) {
 	var out []Nudge
 	if err := c.call(ctx, MethodRecentNudges, nReq{N: n}, &out); err != nil {

internal/ipc/server.go

@@ -132,6 +132,22 @@ func (a *storeAPI) CalendarEvents(ctx context.Context, from, to time.Time) ([]Fa
 	return out, nil
 }
 
+func (a *storeAPI) RecentEcosystemTraces(ctx context.Context, n int) ([]EcosystemTrace, error) {
+	trs, err := a.s.RecentEcosystemTraces(ctx, n)
+	if err != nil {
+		return nil, mapErr(err)
+	}
+	out := make([]EcosystemTrace, len(trs))
+	for i, tr := range trs {
+		out[i] = EcosystemTrace{
+			ID: tr.ID, Ts: tr.Ts, Service: tr.Service, Operation: tr.Operation,
+			Status: tr.Status, DurationMs: tr.DurationMs, CorrelationID: tr.CorrelationID,
+			CausationID: tr.CausationID, HTTPStatus: tr.HTTPStatus, Fields: tr.Fields,
+		}
+	}
+	return out, nil
+}
+
 func (a *storeAPI) RecentNudges(ctx context.Context, n int) ([]Nudge, error) {
 	ns, err := a.s.RecentNudges(ctx, n)
 	if err != nil {
@@ -774,6 +790,16 @@ var methodTable = map[Method]handlerFunc{
 		}
 		return out, nil
 	}),
+	MethodRecentEcoTraces: withParams(func(ctx context.Context, api CoreAPI, p nReq) ([]EcosystemTrace, error) {
+		out, err := api.RecentEcosystemTraces(ctx, p.N)
+		if err != nil {
+			return nil, err
+		}
+		if out == nil {
+			out = []EcosystemTrace{}
+		}
+		return out, nil
+	}),
 	MethodRecentNudges: withParams(func(ctx context.Context, api CoreAPI, p nReq) ([]Nudge, error) {
 		out, err := api.RecentNudges(ctx, p.N)
 		if err != nil {

internal/ipc/unimplemented.go

@@ -68,6 +68,9 @@ func (UnimplementedCoreAPI) CalendarEvents(ctx context.Context, from, to time.Ti
 func (UnimplementedCoreAPI) RecentNudges(ctx context.Context, n int) ([]Nudge, error) {
 	return nil, ErrNotImplemented
 }
+func (UnimplementedCoreAPI) RecentEcosystemTraces(ctx context.Context, n int) ([]EcosystemTrace, error) {
+	return nil, ErrNotImplemented
+}
 func (UnimplementedCoreAPI) WriteNote(ctx context.Context, ts time.Time, text string, embedding []float32, source string) (int64, error) {
 	return 0, ErrNotImplemented
 }

internal/ipc/wire.go

@@ -27,6 +27,7 @@ const (
 	MethodRecentFacts            Method = "recent_facts"
 	MethodCalendarEvents         Method = "calendar_events"
 	MethodRecentNudges           Method = "recent_nudges"
+	MethodRecentEcoTraces        Method = "recent_ecosystem_traces"
 	MethodWriteNote              Method = "write_note"
 	MethodQueryNotes             Method = "query_notes"
 	MethodRecentNotes            Method = "recent_notes"

internal/store/ecotraces.go

@@ -0,0 +1,107 @@
+package store
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"time"
+)
+
+// ecosystemTraceRetention is how many trace rows are kept. Traces are
+// diagnostics with a short useful life, and they arrive at machine rate, so
+// the table is bounded rather than append-only. The facts table is the audit
+// trail; this one is not.
+const ecosystemTraceRetention = 5000
+
+// EcosystemTrace is one hop of a cross-service call: which service, which
+// operation, how it ended, how long it took, and the ids that stitch the hops
+// of one turn together. Fields carries the hop-specific detail (entity id,
+// capability, failure class) as a JSON object.
+type EcosystemTrace struct {
+	ID            int64          `json:"id"`
+	Ts            time.Time      `json:"ts"`
+	Service       string         `json:"service"`
+	Operation     string         `json:"operation"`
+	Status        string         `json:"status"`
+	DurationMs    int64          `json:"duration_ms"`
+	CorrelationID string         `json:"correlation_id"`
+	CausationID   string         `json:"causation_id"`
+	HTTPStatus    int            `json:"http_status"`
+	Fields        map[string]any `json:"fields"`
+}
+
+// WriteEcosystemTrace appends one trace row and keeps the table bounded.
+func (s *Store) WriteEcosystemTrace(ctx context.Context, tr EcosystemTrace) (int64, error) {
+	fields := "{}"
+	if len(tr.Fields) > 0 {
+		b, err := json.Marshal(tr.Fields)
+		if err != nil {
+			return 0, fmt.Errorf("marshal trace fields: %w", err)
+		}
+		fields = string(b)
+	}
+	res, err := s.db.ExecContext(ctx, `
+		INSERT INTO ecosystem_traces
+		       (ts, service, operation, status, duration_ms, correlation_id, causation_id, http_status, fields)
+		VALUES (?,?,?,?,?,?,?,?,?)`,
+		tr.Ts.UnixMilli(), tr.Service, tr.Operation, tr.Status, tr.DurationMs,
+		tr.CorrelationID, tr.CausationID, tr.HTTPStatus, fields)
+	if err != nil {
+		return 0, fmt.Errorf("write ecosystem trace: %w", err)
+	}
+	id, err := res.LastInsertId()
+	if err != nil {
+		return 0, fmt.Errorf("last insert id: %w", err)
+	}
+	// Prune rarely: the cost of the delete is not worth paying on every hop,
+	// and the bound is a ceiling, not an exact size.
+	if id%256 == 0 {
+		if err := s.PruneEcosystemTraces(ctx, ecosystemTraceRetention); err != nil {
+			return id, err
+		}
+	}
+	return id, nil
+}
+
+// PruneEcosystemTraces drops all but the newest keep rows.
+func (s *Store) PruneEcosystemTraces(ctx context.Context, keep int) error {
+	if keep <= 0 {
+		return nil
+	}
+	_, err := s.db.ExecContext(ctx, `
+		DELETE FROM ecosystem_traces
+		 WHERE id <= (SELECT MAX(id) FROM ecosystem_traces) - ?`, keep)
+	if err != nil {
+		return fmt.Errorf("prune ecosystem traces: %w", err)
+	}
+	return nil
+}
+
+// RecentEcosystemTraces returns the newest n traces, newest first.
+func (s *Store) RecentEcosystemTraces(ctx context.Context, n int) ([]EcosystemTrace, error) {
+	rows, err := s.db.QueryContext(ctx, `
+		SELECT id, ts, service, operation, status, duration_ms, correlation_id, causation_id, http_status, fields
+		  FROM ecosystem_traces
+		 ORDER BY id DESC
+		 LIMIT ?`, n)
+	if err != nil {
+		return nil, fmt.Errorf("recent ecosystem traces: %w", err)
+	}
+	defer rows.Close()
+	var out []EcosystemTrace
+	for rows.Next() {
+		var tr EcosystemTrace
+		var tsMilli int64
+		var fields string
+		if err := rows.Scan(&tr.ID, &tsMilli, &tr.Service, &tr.Operation, &tr.Status,
+			&tr.DurationMs, &tr.CorrelationID, &tr.CausationID, &tr.HTTPStatus, &fields); err != nil {
+			return nil, err
+		}
+		tr.Ts = time.UnixMilli(tsMilli).UTC()
+		if fields != "" {
+			_ = json.Unmarshal([]byte(fields), &tr.Fields)
+		}
+		out = append(out, tr)
+	}
+	return out, rows.Err()
+}

internal/store/migrations.go

@@ -160,6 +160,30 @@ ALTER TABLE reminders ADD COLUMN next_fire_ts INTEGER;`, // #2
 	);
 	CREATE UNIQUE INDEX IF NOT EXISTS idx_tasks_live_norm ON tasks (norm) WHERE status IN ('candidate','open');
 	CREATE INDEX IF NOT EXISTS idx_tasks_status ON tasks (status, created_ts DESC);`,
+
+	// #15 — ecosystem call traces (Vikunja #273). Deliberately NOT facts.
+	// Traces are written at machine rate, one act turn produces three or four,
+	// while facts are written at human rate. Sharing the facts table made every
+	// bounded reader of facts (the habit profile's 2000-row window, memeval's
+	// prompt snapshot, /dash's 50 and /history's 200) read mostly traces after
+	// a day of ecosystem use, pushing the rows that matter out of range.
+	// Retention is enforced on write (PruneEcosystemTraces) because nothing
+	// here is an audit trail: a trace answers "did this hop work" for as long
+	// as anyone is still asking.
+	`CREATE TABLE IF NOT EXISTS ecosystem_traces (
+		id             INTEGER PRIMARY KEY AUTOINCREMENT,
+		ts             INTEGER NOT NULL,
+		service        TEXT    NOT NULL,
+		operation      TEXT    NOT NULL,
+		status         TEXT    NOT NULL,
+		duration_ms    INTEGER NOT NULL DEFAULT 0,
+		correlation_id TEXT    NOT NULL DEFAULT '',
+		causation_id   TEXT    NOT NULL DEFAULT '',
+		http_status    INTEGER NOT NULL DEFAULT 0,
+		fields         TEXT    NOT NULL DEFAULT '{}'
+	);
+	CREATE INDEX IF NOT EXISTS idx_eco_traces_ts ON ecosystem_traces (ts DESC);
+	CREATE INDEX IF NOT EXISTS idx_eco_traces_correlation ON ecosystem_traces (correlation_id);`,
 }
 
 // migrate applies every migration with a number greater than the DB's current