feat: add conversation with grounded replies, sample mind and M1 acceptance test
Phase 8, completing milestone M1. A user message is stored and appended as an observation event carrying trust, actor, channel and reference. The perceive process analyses it deterministically (intent, introspection kind, entities, claims, urgency) and, within the per-cycle model allowance, enriches it through the perceive prompt. Its handler writes a perception event, an episodic memory with participants, turns claims into beliefs whose evidence is the message, and builds a response intent from state: beliefs and memories for the topic, evidence rows for why-questions, the uncertain band, contested beliefs and their links, recent learning, status changes, and honest declines for subsystems that do not exist yet or for requests with no capabilities. The respond prompt phrases the intent when a model is assigned; otherwise the reply is a direct rendering of the intent. response_generated cites the message, the perception, every belief and memory used, the episode and the model call. API: conversations, messages with optional wait, one-shot ask; chat UI with live refresh and a per-reply intent view. Sample mind Dani as a strictly decoded seed document with an import endpoint and noemactl mind import. tests/m1 drives all fourteen milestone steps including restart.
This commit is contained in:
Andy Dixon
@@ -0,0 +1,238 @@
|
||||
// Package m1 is the acceptance test for the first usable milestone: start,
|
||||
// log in, create a mind, shape its personality, configure a model, chat,
|
||||
// watch events, inspect working memory, the workspace, memories, beliefs and
|
||||
// provenance, restart, and continue the same mind.
|
||||
package m1
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/andydixon/noema/internal/api"
|
||||
"github.com/andydixon/noema/internal/app"
|
||||
"github.com/andydixon/noema/internal/audit"
|
||||
"github.com/andydixon/noema/internal/auth"
|
||||
"github.com/andydixon/noema/internal/beliefs"
|
||||
"github.com/andydixon/noema/internal/brain"
|
||||
"github.com/andydixon/noema/internal/cognition"
|
||||
"github.com/andydixon/noema/internal/config"
|
||||
"github.com/andydixon/noema/internal/conversation"
|
||||
evstore "github.com/andydixon/noema/internal/events"
|
||||
"github.com/andydixon/noema/internal/llm"
|
||||
"github.com/andydixon/noema/internal/llm/prompts"
|
||||
"github.com/andydixon/noema/internal/llm/router"
|
||||
"github.com/andydixon/noema/internal/memory"
|
||||
"github.com/andydixon/noema/internal/minds"
|
||||
"github.com/andydixon/noema/internal/observability"
|
||||
"github.com/andydixon/noema/internal/scheduler"
|
||||
"github.com/andydixon/noema/internal/security/secrets"
|
||||
"github.com/andydixon/noema/internal/storage"
|
||||
"github.com/andydixon/noema/migrations"
|
||||
"github.com/andydixon/noema/pkg/events"
|
||||
)
|
||||
|
||||
type harness struct {
|
||||
t *testing.T
|
||||
deps app.Deps
|
||||
group *scheduler.Group
|
||||
srv *httptest.Server
|
||||
token string
|
||||
}
|
||||
|
||||
// start assembles the daemon the way cmd/noemad does, with a fake model.
|
||||
func start(t *testing.T, deps app.Deps, perceive, respond llm.LanguageModel) *harness {
|
||||
t.Helper()
|
||||
ctx := context.Background()
|
||||
group := scheduler.NewGroup(ctx, deps.Log)
|
||||
registry := brain.NewRegistry().AddProcess(cognition.Attend{}).AddProcess(cognition.Retrieve{}).AddProcess(cognition.Associate{}).AddProcess(cognition.Perceive{})
|
||||
cognition.Handlers{Memory: deps.Memory, Beliefs: deps.Beliefs, Conversations: deps.Conversations}.Register(registry)
|
||||
deps.LLM.Override = map[llm.Role]llm.LanguageModel{llm.RolePerceive: perceive, llm.RoleRespond: respond}
|
||||
deps.Brain = brain.NewManager(brain.Config{DB: deps.DB, Events: deps.Events, Minds: deps.Minds, Registry: registry, Pool: scheduler.NewPool(4), Log: deps.Log, Metrics: deps.Metrics,
|
||||
Services: brain.Services{Events: deps.Events, Memory: deps.Memory, Beliefs: deps.Beliefs, LLM: deps.LLM, Prompts: deps.Prompts}}, group)
|
||||
if err := deps.Brain.Start(ctx); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
s := api.New(deps, nil)
|
||||
h := &harness{t: t, deps: deps, group: group, srv: httptest.NewServer(s.Handler())}
|
||||
return h
|
||||
}
|
||||
|
||||
func (h *harness) stop() {
|
||||
h.srv.Close()
|
||||
h.group.Stop()
|
||||
}
|
||||
|
||||
func (h *harness) do(method, path string, body any, out any) int {
|
||||
h.t.Helper()
|
||||
var rd *strings.Reader
|
||||
if body != nil {
|
||||
b, _ := json.Marshal(body)
|
||||
rd = strings.NewReader(string(b))
|
||||
} else {
|
||||
rd = strings.NewReader("")
|
||||
}
|
||||
req, _ := http.NewRequest(method, h.srv.URL+path, rd)
|
||||
req.Header.Set("Authorization", "Bearer "+h.token)
|
||||
req.Header.Set("Content-Type", "application/json")
|
||||
res, err := http.DefaultClient.Do(req)
|
||||
if err != nil {
|
||||
h.t.Fatal(err)
|
||||
}
|
||||
defer res.Body.Close()
|
||||
if out != nil {
|
||||
json.NewDecoder(res.Body).Decode(out) //nolint:errcheck
|
||||
}
|
||||
return res.StatusCode
|
||||
}
|
||||
|
||||
func TestFirstMilestone(t *testing.T) {
|
||||
pool := storage.TestPool(t, migrations.FS)
|
||||
ctx := context.Background()
|
||||
log := slog.New(slog.DiscardHandler)
|
||||
cfg := config.Defaults()
|
||||
cfg.DatabaseURL = "postgres://test"
|
||||
sec, _ := secrets.New("")
|
||||
llmStore := router.NewStore(pool)
|
||||
deps := app.Deps{Config: cfg, Log: log, DB: pool, Auth: auth.NewService(pool, time.Hour, 2*time.Hour), Audit: audit.New(pool, log), Metrics: observability.NewMetrics(),
|
||||
Minds: minds.NewStore(pool), Events: evstore.NewStore(pool, evstore.NewBus(64), nil), Memory: memory.NewStore(ctx, pool, nil), Beliefs: beliefs.NewStore(pool),
|
||||
Conversations: conversation.NewStore(pool), Secrets: sec, LLMStore: llmStore, LLM: router.NewRouter(llmStore, sec, log, nil, 2), Prompts: prompts.NewStore(pool), Migrations: migrations.FS, Started: time.Now()}
|
||||
if _, err := deps.Prompts.SeedDefaults(ctx); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
// 1–2. Start and "log in": an administrator with an API token.
|
||||
u, err := deps.Auth.CreateUser(ctx, "admin", "administrator-pass", auth.RoleAdministrator)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
token, _ := deps.Auth.CreateAPIToken(ctx, u.ID, "m1", nil)
|
||||
perceive := &llm.Fake{ModelName: "fake-perceive", Script: []string{`{"intent":"statement","summary":"claims a disk failure","entities":[{"name":"atlas","kind":"system"}],"claims":[{"proposition":"atlas has a failing disk","certainty":"asserted"}],"questions":[],"urgency":0.6,"sentiment":-0.3}`}}
|
||||
respond := &llm.Fake{ModelName: "fake-respond", Script: []string{"Noted: I now hold that atlas has a failing disk, on your word alone.", "Atlas: I believe its disk is failing, tentatively.", "Still here after the restart; atlas' disk is still my concern."}}
|
||||
h := start(t, deps, perceive, respond)
|
||||
h.token = token
|
||||
|
||||
// 3. Create a mind.
|
||||
var mind minds.Mind
|
||||
if code := h.do("POST", "/api/v1/minds", map[string]any{"slug": "m1", "display_name": "M1"}, &mind); code != 201 {
|
||||
t.Fatalf("create mind: %d", code)
|
||||
}
|
||||
// 4. Configure personality.
|
||||
p := mind.Personality
|
||||
p.Identity.Role = "acceptance tester"
|
||||
p.Traits["scepticism"] = 0.9
|
||||
var ver minds.Version
|
||||
if code := h.do("PUT", "/api/v1/minds/m1/personality", map[string]any{"personality": p, "change_note": "m1"}, &ver); code != 200 || ver.Version != 2 {
|
||||
t.Fatalf("personality: %d %+v", code, ver)
|
||||
}
|
||||
// 5. Configure an LLM: a provider and model exist in configuration; calls are served by the fake via role override.
|
||||
var prov router.Provider
|
||||
if code := h.do("POST", "/api/v1/llm/providers", map[string]any{"name": "fake", "kind": "ollama", "endpoint": "http://127.0.0.1:1", "allow_private": true}, &prov); code != 201 {
|
||||
t.Fatalf("provider: %d", code)
|
||||
}
|
||||
// 6. Chat: a statement, then a question.
|
||||
var ask struct {
|
||||
Reply *conversation.Message `json:"reply"`
|
||||
Note string `json:"note"`
|
||||
}
|
||||
if code := h.do("POST", "/api/v1/minds/m1/ask", map[string]any{"text": "atlas has a failing disk.", "wait_seconds": 20}, &ask); code != 200 || ask.Reply == nil {
|
||||
t.Fatalf("ask 1: %d %+v", code, ask)
|
||||
}
|
||||
if !strings.Contains(ask.Reply.Content, "Noted") || ask.Reply.LLMCallID.IsZero() || ask.Reply.EventID.IsZero() {
|
||||
t.Fatalf("reply 1 not from model with provenance: %+v", ask.Reply)
|
||||
}
|
||||
var intent cognition.Intent
|
||||
json.Unmarshal(ask.Reply.Intent, &intent) //nolint:errcheck
|
||||
if intent.Kind != "acknowledge" || len(intent.Beliefs) != 1 {
|
||||
t.Fatalf("intent 1 wrong: %+v", intent)
|
||||
}
|
||||
if code := h.do("POST", "/api/v1/minds/m1/ask", map[string]any{"text": "What do you believe about atlas?", "wait_seconds": 20}, &ask); code != 200 || ask.Reply == nil {
|
||||
t.Fatalf("ask 2: %d %+v", code, ask)
|
||||
}
|
||||
json.Unmarshal(ask.Reply.Intent, &intent) //nolint:errcheck
|
||||
if intent.Kind != "introspect" || len(intent.Beliefs) == 0 || !strings.Contains(intent.Beliefs[0].Proposition, "failing disk") {
|
||||
t.Fatalf("intent 2 not grounded in the recorded belief: %+v", intent)
|
||||
}
|
||||
// 7. Cognitive events appeared, with the pipeline shape.
|
||||
var evs struct{ Items []events.Event }
|
||||
h.do("GET", "/api/v1/minds/m1/events?limit=200", nil, &evs)
|
||||
types := map[events.Type]int{}
|
||||
for _, e := range evs.Items {
|
||||
types[e.Type]++
|
||||
}
|
||||
for _, want := range []events.Type{events.Observation, events.Perception, events.ThoughtCandidate, events.ThoughtSelected, events.WorkspaceBroadcast, events.MemoryCreated, events.BeliefCreated, events.LLMResponse, events.ResponseGenerated} {
|
||||
if types[want] == 0 {
|
||||
t.Fatalf("missing event type %s in %v", want, types)
|
||||
}
|
||||
}
|
||||
// 8–9. Working memory and workspace are inspectable.
|
||||
var ws api.WorkspaceView
|
||||
h.do("GET", "/api/v1/minds/m1/workspace", nil, &ws)
|
||||
if !ws.Running || ws.State.Cycle < 2 || len(ws.State.WorkingMemory) == 0 || len(ws.Candidates) == 0 {
|
||||
t.Fatalf("workspace: %+v", ws.State)
|
||||
}
|
||||
// 10. Episodic memories.
|
||||
var mems struct{ Items []memory.Memory }
|
||||
h.do("GET", "/api/v1/minds/m1/memories?kind=episodic", nil, &mems)
|
||||
if len(mems.Items) < 2 {
|
||||
t.Fatalf("expected episodic memories, got %d", len(mems.Items))
|
||||
}
|
||||
// 11–12. Beliefs with provenance back to the message.
|
||||
var bs struct{ Items []beliefs.Belief }
|
||||
h.do("GET", "/api/v1/minds/m1/beliefs", nil, &bs)
|
||||
if len(bs.Items) != 1 || bs.Items[0].Epistemic != "claim" {
|
||||
t.Fatalf("beliefs: %+v", bs.Items)
|
||||
}
|
||||
var detail api.BeliefDetail
|
||||
h.do("GET", "/api/v1/minds/m1/beliefs/"+string(bs.Items[0].ID), nil, &detail)
|
||||
if len(detail.Evidence) != 1 || detail.Evidence[0].Kind != "event" || detail.Breakdown.SourcesFor != 1 {
|
||||
t.Fatalf("provenance: %+v", detail)
|
||||
}
|
||||
var evCtx api.EventContext
|
||||
h.do("GET", "/api/v1/events/"+string(detail.Evidence[0].RefID)+"/context", nil, &evCtx)
|
||||
if evCtx.Event.Type != events.Observation || len(evCtx.Children) == 0 {
|
||||
t.Fatalf("event context: %+v", evCtx.Event)
|
||||
}
|
||||
var respCtx api.EventContext
|
||||
h.do("GET", "/api/v1/events/"+string(ask.Reply.EventID)+"/context", nil, &respCtx)
|
||||
var citesBelief bool
|
||||
for _, ref := range respCtx.Event.Evidence {
|
||||
if ref.Kind == "belief" {
|
||||
citesBelief = true
|
||||
}
|
||||
}
|
||||
if !citesBelief || respCtx.Cause == nil || respCtx.Cause.Type != events.Perception {
|
||||
t.Fatalf("reply event lacks provenance: %+v", respCtx.Event)
|
||||
}
|
||||
|
||||
// 13. Restart everything except the database.
|
||||
cycleBefore := ws.State.Cycle
|
||||
h.stop()
|
||||
h2 := start(t, deps, perceive, respond)
|
||||
defer h2.stop()
|
||||
h2.token = token
|
||||
var ws2 api.WorkspaceView
|
||||
h2.do("GET", "/api/v1/minds/m1/workspace", nil, &ws2)
|
||||
if !ws2.Running || ws2.State.Cycle != cycleBefore || len(ws2.State.WorkingMemory) != len(ws.State.WorkingMemory) {
|
||||
t.Fatalf("state not continued after restart: before %d/%d after %d/%d", cycleBefore, len(ws.State.WorkingMemory), ws2.State.Cycle, len(ws2.State.WorkingMemory))
|
||||
}
|
||||
// 14. Continue the same mind: it still holds the belief and answers.
|
||||
if code := h2.do("POST", "/api/v1/minds/m1/ask", map[string]any{"text": "What do you believe about atlas?", "wait_seconds": 20}, &ask); code != 200 || ask.Reply == nil {
|
||||
t.Fatalf("ask after restart: %d %+v", code, ask)
|
||||
}
|
||||
json.Unmarshal(ask.Reply.Intent, &intent) //nolint:errcheck
|
||||
if len(intent.Beliefs) == 0 {
|
||||
t.Fatalf("belief lost across restart: %+v", intent)
|
||||
}
|
||||
var bs2 struct{ Items []beliefs.Belief }
|
||||
h2.do("GET", "/api/v1/minds/m1/beliefs", nil, &bs2)
|
||||
if len(bs2.Items) != 1 || bs2.Items[0].ID != bs.Items[0].ID {
|
||||
t.Fatalf("belief identity changed: %+v", bs2.Items)
|
||||
}
|
||||
fmt.Println("M1 acceptance: events", len(evs.Items), "cycles", ws2.State.Cycle)
|
||||
}
|
||||
Reference in New Issue
Block a user