Files
Maven/cmd/mavend/ecosystem_acts.go
T
kami 927e46bca3 Version, authenticate and fully trace ecosystem calls (#273)
Every Nexus and Praxis request now carries the contract version, an
X-Requested-By identifying Maven, a correlation ID (generated per request
when the call is not part of a traced action), and a bearer token when
one is configured. Nexus/Praxis/Hexis config blocks grew an optional
token field, env-expandable so the secret stays out of the committed
config; the vendored hexis client predates bearer auth, so a configured
Hexis token logs a loud warning instead of pretending to authenticate.

Client failures are now a typed *ecosystemError carrying service,
operation and HTTP status, classifying unauthorized, contract-mismatch
and unreachable without matching on message text.

Trace records are written for resolution, discovery, confirmation and
execution — on failure as well as success — with status, duration,
correlation and causation ids, HTTP status and failure class, and the
utterance redacted to its length. Traces were never actually persisted
before: both trace writers used fact kind "system", which the store's
CHECK constraint rejects, and the error was discarded.
2026-08-01 06:57:52 +04:00

537 lines
19 KiB
Go
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
package main
import (
"context"
"encoding/json"
"errors"
"fmt"
"log"
"strings"
"time"
hexisclient "github.com/kami/hexis/pkg/client"
"github.com/kami/maven/internal/ipc"
"github.com/kami/maven/internal/router"
)
// praxisCapability is one arm of the Praxis act dispatch. This is an interface
// rather than a map[string]func because each arm carries its own state: the
// verb aliases it answers to, the trace name it records, and its own reply
// formatting. The dispatch grows an arm per Praxis capability, so a new one is
// added to praxisCapabilities below and nothing else changes.
type praxisCapability interface {
// aliases are the verbs (router fn slots, EN and RU) this capability answers to.
aliases() []string
// handle runs the capability and returns the user-facing reply.
handle(ctx context.Context, h *reactiveHandler, px *praxisClient, dec router.Decision) string
}
// praxisCapabilities is the registry handlePraxisAct consults, in order.
var praxisCapabilities = []praxisCapability{
listAttentionCapability{},
praxisItemAction{
verbs: []string{"acknowledge_item", "принято", "понял", "поняла"},
ask: "какой пункт отметить принятым?",
op: "acknowledge",
failure: "не получилось отметить принятым.",
success: "принято.",
call: func(ctx context.Context, px *praxisClient, id string) error {
_, err := px.Acknowledge(ctx, id)
return err
},
},
praxisItemAction{
verbs: []string{"resolve_item", "сделано", "готово", "решено"},
ask: "какой пункт отметить сделанным?",
op: "resolve",
failure: "не получилось отметить сделанным.",
success: "отмечено как сделано.",
call: func(ctx context.Context, px *praxisClient, id string) error {
_, err := px.Resolve(ctx, id)
return err
},
},
praxisItemAction{
verbs: []string{"ignore_item", "игнорировать", "неважно"},
ask: "какой пункт игнорировать?",
op: "ignore",
failure: "не получилось проигнорировать.",
success: "проигнорировано.",
call: func(ctx context.Context, px *praxisClient, id string) error {
_, err := px.Ignore(ctx, id)
return err
},
},
praxisItemAction{
verbs: []string{"pin_item", "закрепить"},
ask: "какой пункт закрепить?",
op: "pin",
failure: "не получилось закрепить.",
success: "закреплено.",
call: func(ctx context.Context, px *praxisClient, id string) error {
_, err := px.Pin(ctx, id, true)
return err
},
},
listChangesCapability{},
entityAttentionCapability{},
}
// handlePraxisAct — dispatches ecosystem tool acts through the Praxis tools API.
// Returns "" when the act is not a Praxis verb (the caller falls through to the
// system command executor). Returns a reply string otherwise.
func (h *reactiveHandler) handlePraxisAct(ctx context.Context, dec router.Decision) string {
if h.ecosystem == nil || h.ecosystem.praxis == nil {
return ""
}
px := h.ecosystem.praxis
for _, capability := range praxisCapabilities {
for _, alias := range capability.aliases() {
if alias == dec.Slots.Fn {
return capability.handle(ctx, h, px, dec)
}
}
}
// Not a Praxis verb — let the caller fall through.
return ""
}
// praxisItemAction is the shared shape of the item-lifecycle capabilities: take
// an item id from the value slot, call one Praxis endpoint, trace the result.
type praxisItemAction struct {
verbs []string
ask string // reply when no item id was given
op string // trace + log name of the operation
failure string // reply when the Praxis call errors
success string
call func(ctx context.Context, px *praxisClient, id string) error
}
func (a praxisItemAction) aliases() []string { return a.verbs }
func (a praxisItemAction) handle(ctx context.Context, h *reactiveHandler, px *praxisClient, dec router.Decision) string {
id := dec.Slots.Value
if id == "" {
return a.ask
}
if err := a.call(ctx, px, id); err != nil {
log.Printf("ecosystem: praxis %s %s: %v", a.op, id, err)
return a.failure
}
h.recordPraxisTrace(ctx, a.op, map[string]any{"item_id": id})
return a.success
}
// listAttentionCapability reads the attention digest and surfaces every item it speaks.
type listAttentionCapability struct{}
func (listAttentionCapability) aliases() []string {
return []string{"list_attention", "attention", "внимание", "что требует внимания", "что нового"}
}
func (listAttentionCapability) handle(ctx context.Context, h *reactiveHandler, px *praxisClient, _ router.Decision) string {
items, err := px.ListAttention(ctx, 20)
if err != nil {
log.Printf("ecosystem: praxis attention: %v", err)
return "не могу сейчас узнать, что требует внимания."
}
if len(items) == 0 {
return "ничего не требует внимания."
}
h.recordPraxisTrace(ctx, "list_attention", map[string]any{"count": len(items)})
var parts []string
for _, item := range items {
title, _ := item["title"].(string)
// importance arrives as JSON number ⇒ float64 over the HTTP contract.
importance, _ := item["importance"].(float64)
rule, _ := item["rule"].(string)
s := title
if importance > 0 {
s += fmt.Sprintf(" (важность %d", int(importance))
if rule != "" {
s += ": " + rule
}
s += ")"
}
parts = append(parts, s)
// Speaking an item surfaces it, it does not acknowledge it
// (ECOSYSTEM-SPEC.md §2.3: surfaced != acknowledged). Best-effort:
// a failed surface call must not block delivering the digest.
if id, ok := item["id"].(string); ok && id != "" {
if _, err := px.Surface(ctx, id); err != nil {
log.Printf("ecosystem: praxis surface %s: %v", id, err)
}
}
}
return "требует внимания: " + strings.Join(parts, "; ")
}
// listChangesCapability reads the recent-changes feed.
type listChangesCapability struct{}
func (listChangesCapability) aliases() []string {
return []string{"list_changes", "changes", "изменения", "что изменилось"}
}
func (listChangesCapability) handle(ctx context.Context, h *reactiveHandler, px *praxisClient, _ router.Decision) string {
changes, err := px.ListChanges(ctx, 20)
if err != nil {
log.Printf("ecosystem: praxis changes: %v", err)
return "не могу сейчас узнать об изменениях."
}
if len(changes) == 0 {
return "нет изменений."
}
h.recordPraxisTrace(ctx, "list_changes", map[string]any{"count": len(changes)})
var parts []string
for _, c := range changes {
title, _ := c["title"].(string)
typ, _ := c["change_type"].(string)
parts = append(parts, fmt.Sprintf("%s (%s)", title, typ))
}
return "изменения: " + strings.Join(parts, "; ")
}
// entityAttentionCapability answers "what's going on with X" by resolving X to
// a canonical Nexus entity and asking Praxis for that entity's attention items
// (Vikunja #272). Unlike listAttentionCapability it is scoped: the entity_id
// travels to Praxis as a query parameter instead of Maven filtering an unscoped
// list client-side, which is what makes the ref canonical end to end.
//
// It also folds in what Maven herself knows about the same entity — facts the
// enrichment worker has already resolved to that entity_id — so one question
// gets one answer across both stores.
type entityAttentionCapability struct{}
func (entityAttentionCapability) aliases() []string {
return []string{"entity_attention", "что с", "как дела у", "статус"}
}
func (entityAttentionCapability) handle(ctx context.Context, h *reactiveHandler, px *praxisClient, dec router.Decision) string {
subject := dec.Slots.Value
if subject == "" {
subject = dec.Slots.Text
}
if subject == "" {
return "про что именно спросить?"
}
if h.ecosystem == nil || h.ecosystem.nexus == nil {
// Without Nexus there is no canonical ref to scope by. Say so rather
// than quietly answering about something else.
return "не могу связать это с сущностью — Nexus не настроен."
}
entityID, displayName, ambiguous, err := h.ecosystem.resolveEntityReference(ctx, subject, nil)
if err != nil {
log.Printf("ecosystem: entity attention resolve %q: %v", subject, err)
return "экосистема недоступна, попробуй ещё раз."
}
if len(ambiguous) > 0 {
return "уточни, что именно: " + strings.Join(ambiguous, ", ") + "?"
}
if entityID == "" {
return "не знаю такой сущности."
}
if displayName == "" {
displayName = subject
}
items, err := px.ListAttentionForEntity(ctx, entityID, 20)
if err != nil {
log.Printf("ecosystem: praxis attention for %s: %v", entityID, err)
return "не могу сейчас узнать, что требует внимания по «" + displayName + "»."
}
h.recordPraxisTrace(ctx, "entity_attention", map[string]any{
"entity_id": entityID, "count": len(items),
})
var parts []string
for _, item := range items {
title, _ := item["title"].(string)
if title == "" {
continue
}
parts = append(parts, title)
// Same surfaced != acknowledged rule as the unscoped digest.
if id, ok := item["id"].(string); ok && id != "" {
if _, err := px.Surface(ctx, id); err != nil {
log.Printf("ecosystem: praxis surface %s: %v", id, err)
}
}
}
if known := h.localFactsForEntity(ctx, entityID); known != "" {
parts = append(parts, known)
}
if len(parts) == 0 {
return "по «" + displayName + "» ничего нет."
}
return "по «" + displayName + "»: " + strings.Join(parts, "; ")
}
// localFactsForEntity summarises Maven's own facts already resolved to this
// canonical entity. Empty when the store is unavailable or nothing matched —
// entity-scoped memory is an enrichment of the answer, never a precondition.
func (h *reactiveHandler) localFactsForEntity(ctx context.Context, entityID string) string {
if h.dataStore == nil || entityID == "" {
return ""
}
facts, err := h.dataStore.FactsByEntity(ctx, entityID, 3)
if err != nil {
log.Printf("ecosystem: facts by entity %s: %v", entityID, err)
return ""
}
var parts []string
for _, f := range facts {
if f.Value != "" {
parts = append(parts, f.Value)
}
}
if len(parts) == 0 {
return ""
}
return "я помню: " + strings.Join(parts, ", ")
}
// mergeFields overlays b onto a and returns a.
func mergeFields(a, b map[string]any) map[string]any {
for k, v := range b {
a[k] = v
}
return a
}
// recordPraxisTrace — writes a fact recording a cross-service ecosystem call.
// The fact is stored with source "praxis:trace" so the proactive loop can
// reference it and the dashboard can display recent ecosystem activity.
func (h *reactiveHandler) recordPraxisTrace(ctx context.Context, operation string, details map[string]any) {
now := h.now()
value := operation
if len(details) > 0 {
if b, err := json.Marshal(details); err == nil {
value = operation + " " + string(b)
}
}
// Kind must be one of the store's allowed kinds ('self','env','config');
// "system" was silently rejected by the CHECK constraint, so no praxis
// trace was ever persisted.
if _, err := h.api.WriteFact(ctx, ipc.WriteFactReq{
Ts: now,
Kind: "env",
Key: "praxis:" + operation,
Value: value,
Source: "praxis:trace",
Confidence: 1.0,
}); err != nil {
log.Printf("ecosystem: record praxis trace %s: %v", operation, err)
}
}
// traceStatus classifies an ecosystem call for the trace record. Kept coarse
// on purpose: a trace is read to answer "did this hop work, and how long did
// it take", not to re-derive the error.
const (
traceOK = "ok"
traceFailed = "failed"
traceRefused = "refused" // the far side answered, and said no
traceAmbig = "ambiguous"
traceNotFound = "not_found"
)
// redactSubject reduces a user utterance to something safe to persist in a
// trace: its length only. Traces are diagnostics, and his words are not
// diagnostics — the correlation ID is what ties a trace to the turn.
func redactSubject(s string) string {
return fmt.Sprintf("<%d chars>", len([]rune(s)))
}
// recordEcosystemTrace writes one hop of a cross-service call: which service,
// which operation, the outcome, how long it took, and the correlation ID that
// stitches the hops together. Unlike recordPraxisTrace it is written for every
// outcome, not only success — an unrecorded failure is exactly the hop you
// need when something went wrong at 3am.
func (h *reactiveHandler) recordEcosystemTrace(ctx context.Context, service, op, status string, started time.Time, fields map[string]any) {
details := map[string]any{
"service": service,
"operation": op,
"status": status,
"duration_ms": h.now().Sub(started).Milliseconds(),
}
if id := correlationIDFromCtx(ctx); id != "" {
details["correlation_id"] = id
}
for k, v := range fields {
details[k] = v
}
value := service + ":" + op + " " + status
if b, err := json.Marshal(details); err == nil {
value = value + " " + string(b)
}
if _, err := h.api.WriteFact(ctx, ipc.WriteFactReq{
Ts: h.now(),
Kind: "env",
Key: "ecosystem:" + service + ":" + op,
Value: value,
Source: "ecosystem:trace",
Confidence: 1.0,
}); err != nil {
log.Printf("ecosystem: record trace %s:%s: %v", service, op, err)
}
}
// traceErrorFields describes an ecosystemError for a trace without leaking the
// payload: the HTTP status and the failure class, nothing else.
func traceErrorFields(err error) map[string]any {
fields := map[string]any{}
var ee *ecosystemError
if errors.As(err, &ee) {
fields["http_status"] = ee.Status
switch {
case ee.Unauthorized():
fields["class"] = "unauthorized"
case ee.ContractMismatch():
fields["class"] = "contract_mismatch"
case ee.Unreachable():
fields["class"] = "unreachable"
default:
fields["class"] = "error"
}
return fields
}
fields["class"] = "error"
return fields
}
// handleHexisAct — resolves entity references through Nexus and executes
// matching capabilities through Hexis. Returns a reply string when handled,
// or "" to fall through to the system command executor.
func (h *reactiveHandler) handleHexisAct(ctx context.Context, dec router.Decision) string {
if h.ecosystem == nil {
return ""
}
// Every hop of this action shares one correlation ID, assigned here so
// resolution and discovery are traceable even when execution never
// happens.
if correlationIDFromCtx(ctx) == "" {
ctx = withCorrelationID(ctx, newCorrelationID())
}
// Resolve the utterance text as an entity reference through Nexus. An
// ambiguous match must stop and clarify — never guess a mutation target.
started := h.now()
entityID, displayName, ambiguous, err := h.ecosystem.resolveEntityReference(ctx, dec.Slots.Text, nil)
if err != nil {
h.recordEcosystemTrace(ctx, "nexus", "resolve", traceFailed, started,
mergeFields(traceErrorFields(err), map[string]any{"subject": redactSubject(dec.Slots.Text)}))
// A genuine Nexus dependency failure, not "no such entity" — stop here
// and report degradation rather than silently falling through to the
// local command executor (ECOSYSTEM-SPEC.md: services degrade
// independently, never a silent all-clear).
return "экосистема недоступна, попробуй ещё раз."
}
if len(ambiguous) > 0 {
h.recordEcosystemTrace(ctx, "nexus", "resolve", traceAmbig, started,
map[string]any{"candidates": len(ambiguous)})
return "уточни, что именно: " + strings.Join(ambiguous, ", ") + "?"
}
if entityID == "" {
h.recordEcosystemTrace(ctx, "nexus", "resolve", traceNotFound, started,
map[string]any{"subject": redactSubject(dec.Slots.Text)})
return ""
}
h.recordEcosystemTrace(ctx, "nexus", "resolve", traceOK, started,
map[string]any{"entity_id": entityID})
// Discover Hexis capabilities for this entity. A resolved entity with a
// genuine Hexis failure must not be treated as "no capabilities" and
// fall through to unrelated local execution.
discovered := h.now()
caps, err := h.ecosystem.discoverCapabilities(ctx, entityID)
if err != nil {
h.recordEcosystemTrace(ctx, "hexis", "capabilities", traceFailed, discovered,
mergeFields(traceErrorFields(err), map[string]any{"entity_id": entityID}))
return "экосистема недоступна, попробуй ещё раз."
}
h.recordEcosystemTrace(ctx, "hexis", "capabilities", traceOK, discovered,
map[string]any{"entity_id": entityID, "count": len(caps)})
if len(caps) == 0 {
return ""
}
// Match the user's verb to a capability by name/description. Collect all
// matches: more than one is itself ambiguous, so we ask rather than pick
// the first (ecosystem invariant: no arbitrary target for mutation).
verb := dec.Slots.Fn
if verb == "" {
verb = dec.Slots.Text
}
verbLower := strings.ToLower(verb)
var matches []*hexisclient.Capability
for i, c := range caps {
if strings.Contains(strings.ToLower(c.Name), verbLower) ||
(c.Description != "" && strings.Contains(strings.ToLower(c.Description), verbLower)) {
matches = append(matches, &caps[i])
}
}
if len(matches) == 0 {
return ""
}
if len(matches) > 1 {
var names []string
for _, m := range matches {
names = append(names, m.Name)
}
return "какую команду для " + displayName + ": " + strings.Join(names, ", ") + "?"
}
matched := matches[0]
// Read-only capabilities run immediately; mutating ones are parked for an
// explicit spoken confirm bound to this capability + target.
if !matched.ReadOnly {
h.mu.Lock()
h.pendingHexis = &pendingHexisExec{
capabilityID: matched.ID,
capName: matched.Name,
entityID: entityID,
displayName: displayName,
expiry: h.now().Add(confirmTTL),
}
h.mu.Unlock()
h.recordEcosystemTrace(ctx, "hexis", "confirmation", "pending", h.now(),
map[string]any{"entity_id": entityID, "capability": matched.Name})
return "выполнить «" + matched.Name + "» для " + displayName + "? скажи «да» или «нет»."
}
return h.execHexis(ctx, matched.ID, matched.Name, entityID, displayName)
}
// execHexis runs a resolved capability and records a cross-service trace with
// the correlation ID. It reports command success, never operational recovery
// (Praxis observes recovery independently).
func (h *reactiveHandler) execHexis(ctx context.Context, capID, capName, entityID, displayName string) string {
started := h.now()
causationID := correlationIDFromCtx(ctx)
correlationID, err := h.ecosystem.executeCapability(ctx, capID, entityID, nil)
traced := withCorrelationID(ctx, correlationID)
if err != nil {
log.Printf("ecosystem: hexis execute error (cor=%s): %v", correlationID, err)
h.recordEcosystemTrace(traced, "hexis", "execute", traceFailed, started,
mergeFields(traceErrorFields(err), map[string]any{
"entity_id": entityID, "capability": capName, "causation_id": causationID,
}))
return "не получилось выполнить команду для " + displayName + "."
}
h.recordEcosystemTrace(traced, "hexis", "execute", traceOK, started, map[string]any{
"entity_id": entityID, "capability": capName, "causation_id": causationID,
})
h.recordPraxisTrace(ctx, "hexis:"+capName, map[string]any{
"entity_id": entityID,
"entity_name": displayName,
"capability": capName,
"correlation_id": correlationID,
})
return "команда выполнена для " + displayName + "."
}